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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 30796
    Prev
    Next
    INDEX
    Explanations

    a

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nuit
    -0.07
    ESA
    -0.07
    以上
    -0.06
    _ng
    -0.06
    ná
    -0.06
    _Re
    -0.06
     Пок
    -0.06
    yw
    -0.06
    Ent
    -0.06
     trava
    -0.06
    POSITIVE LOGITS
    rightness
    0.07
     kim
    0.06
    (color
    0.06
     Kylie
    0.06
     CGFloat
    0.06
    /auto
    0.06
     bh
    0.06
    .RIGHT
    0.06
    959
    0.05
     第三
    0.05
    Activations Density 0.042%

    No Known Activations