© 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. 104809
    Prev
    Next
    INDEX
    Explanations

    face features

    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_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
    >p
    -0.07
    ิป
    -0.07
    Um
    -0.07
    gay
    -0.06
    ैस
    -0.06
    EDIA
    -0.06
    Take
    -0.06
    ibaba
    -0.06
    /people
    -0.06
     pants
    -0.06
    POSITIVE LOGITS
     deltaTime
    0.07
     роботи
    0.07
     sharpen
    0.06
    AGING
    0.06
     progressing
    0.06
     trái
    0.06
     rotterdam
    0.06
     Played
    0.06
     targetType
    0.06
     گردش
    0.06
    Activations Density 0.022%

    No Known Activations