© 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. 109781
    Prev
    Next
    INDEX
    Explanations

    costa

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of the wing’s leading‐edge region (the “costa”) in descriptions of moth forewings.

    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
    MYSQL
    -0.07
    "h
    -0.07
     Supplier
    -0.07
    HorizontalAlignment
    -0.07
    博士
    -0.06
    anian
    -0.06
    /n
    -0.06
    ?family
    -0.06
     sắt
    -0.06
    .bootstrap
    -0.06
    POSITIVE LOGITS
     signatures
    0.06
     peny
    0.06
    错误
    0.06
    0.06
    	cerr
    0.06
     pests
    0.06
     месяцев
    0.06
    (fid
    0.06
    лений
    0.06
    uming
    0.05
    Activations Density 0.002%

    No Known Activations