© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54513
    Prev
    Next
    INDEX
    Explanations

    pharmac

    np_max-act · gemini-2.0-flash

    the pharmacological properties and interactions of various compounds, particularly focusing on their effects and mechanisms in medical and research contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects mentions of pharmacology‐related terms, especially words beginning with “pharmac-” (e.g., pharmacological, pharmacokinetics).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jessie
    -0.07
     Density
    -0.07
    ۱۷
    -0.07
     startTime
    -0.07
     televis
    -0.07
     Mutable
    -0.06
    itter
    -0.06
     northeastern
    -0.06
     MetroFramework
    -0.06
     神
    -0.06
    POSITIVE LOGITS
     pharmac
    0.14
     Pharmac
    0.13
    armac
    0.08
    pecial
    0.07
    ACC
    0.07
     unresolved
    0.07
    salary
    0.07
     Nak
    0.07
    verb
    0.07
    /*================================================================
    0.07
    Activations Density 0.004%

    No Known Activations