© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129723
    Prev
    Next
    INDEX
    Explanations

    Monogenea species descriptions

    np_max-act · gemini-2.0-flash

    scientific names and classifications of new species.

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

    The neuron fires on scientific taxonomy labels—especially the Latin names and rank indicators (e.g. Monogenea, Diplectanidae, genus and family names) in the parasite classification.

    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
     Boat
    -0.07
     sino
    -0.07
     сох
    -0.07
     Bug
    -0.06
     Short
    -0.06
     Send
    -0.06
     phon
    -0.06
     Dion
    -0.06
    Sampling
    -0.06
     cuffs
    -0.06
    POSITIVE LOGITS
    辰
    0.06
    否
    0.06
    getClass
    0.06
     herkes
    0.06
     конечно
    0.06
    طع
    0.06
    центра
    0.06
    论文
    0.06
    erras
    0.05
    들이
    0.05
    Activations Density 0.007%

    No Known Activations