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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55827
    Prev
    Next
    INDEX
    Explanations

    pharmacology

    np_max-act · gemini-2.0-flash

    This neuron flags mentions of proteins (especially receptors) being attractive targets for drug or pharmacological therapy.

    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
    _ticks
    -0.07
     tunnel
    -0.06
     потер
    -0.06
     Pall
    -0.06
     Tunnel
    -0.06
     yoktur
    -0.06
    빠
    -0.06
    âce
    -0.06
    testimonial
    -0.06
    .Author
    -0.06
    POSITIVE LOGITS
     reminded
    0.07
    _star
    0.07
    _IDX
    0.06
    _closure
    0.06
     Hollywood
    0.06
    wand
    0.06
    -pages
    0.06
     abol
    0.06
    buttonShape
    0.06
    Monthly
    0.06
    Activations Density 0.020%

    No Known Activations