© 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. 3-RESID-POST-AA
    11. 95259
    Prev
    Next
    INDEX
    Explanations

    also

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ανά
    -0.07
    Sorry
    -0.07
    uem
    -0.06
     více
    -0.06
    ____
    -0.06
    484
    -0.06
    pyx
    -0.06
     shutdown
    -0.06
     ARC
    -0.06
     shampoo
    -0.06
    POSITIVE LOGITS
    -duty
    0.07
    Using
    0.06
    .addTo
    0.06
    contained
    0.06
    +↵
    0.06
    _env
    0.06
     Credentials
    0.06
    ها
    0.06
    IGATION
    0.06
     also
    0.06
    Activations Density 0.044%

    No Known Activations