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. 15-RESID-POST-AA
    6. 109994
    Prev
    Next
    INDEX
    Explanations

    Citations

    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
     대학
    -0.08
    _region
    -0.07
     Ball
    -0.07
     isSelected
    -0.07
    vůli
    -0.07
     pontos
    -0.07
     Alison
    -0.07
    INATION
    -0.07
    .EXTRA
    -0.07
     terör
    -0.06
    POSITIVE LOGITS
     πλα
    0.06
    �
    0.06
    校
    0.06
     ostr
    0.06
    _IDENT
    0.05
    Pawn
    0.05
    erah
    0.05
    .writeFileSync
    0.05
     mailing
    0.05
    を使
    0.05
    Activations Density 0.011%

    No Known Activations