Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 112181
    Prev
    Next
    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lup
    -0.07
     Thumbnails
    -0.07
     penal
    -0.07
    _parameter
    -0.07
     ordeal
    -0.06
     deducted
    -0.06
     jogador
    -0.06
     PAN
    -0.06
    upe
    -0.06
     lottery
    -0.06
    POSITIVE LOGITS
    /filepath
    0.06
     IPV
    0.06
     <<"
    0.06
    ????
    0.06
     proph
    0.06
    стров
    0.06
    Ind
    0.06
    .Types
    0.06
    注册
    0.06
     nive
    0.06
    Activations Density 0.000%

    No Known Activations