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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9819
    Prev
    Next
    INDEX
    Explanations

    contact information

    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
     Weekend
    -0.07
    gross
    -0.07
     bladder
    -0.06
    ,array
    -0.06
    \Admin
    -0.06
     technically
    -0.06
     tic
    -0.06
    nostic
    -0.06
     Jens
    -0.06
    ehicle
    -0.06
    POSITIVE LOGITS
     กรกฎาคม
    0.06
    ░
    0.06
     अस
    0.06
    Brains
    0.06
     Schultz
    0.06
     murders
    0.06
     ده
    0.06
    423
    0.06
     Democracy
    0.06
    常
    0.05
    Activations Density 0.048%

    No Known Activations