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. 11-RESID-POST-AA
    6. 22067
    Prev
    Next
    INDEX
    Explanations

    world records

    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
    ars
    -0.07
     Bra
    -0.07
     alignment
    -0.06
    CBC
    -0.06
    اری
    -0.06
    _usage
    -0.06
    -even
    -0.06
    /status
    -0.06
    เย
    -0.06
    Operators
    -0.06
    POSITIVE LOGITS
    크기
    0.07
    <QString
    0.07
    "]').
    0.06
     Utils
    0.06
     provoked
    0.06
     isKindOfClass
    0.06
     венти
    0.06
     články
    0.06
    .btnExit
    0.06
    _aspect
    0.06
    Activations Density 0.034%

    No Known Activations