© 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. 7-RESID-POST-AA
    11. 46588
    Prev
    Next
    INDEX
    Explanations

    hit

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (matrix
    -0.07
    YY
    -0.06
     SSC
    -0.06
    _la
    -0.06
    .intro
    -0.06
     Nearly
    -0.06
     jente
    -0.06
    Thunk
    -0.06
    Za
    -0.06
    Jak
    -0.06
    POSITIVE LOGITS
    ≡≡
    0.07
     значительно
    0.06
    .OrdinalIgnoreCase
    0.06
    _Pos
    0.06
    (Adapter
    0.06
    向
    0.06
    的
    0.06
     edged
    0.06
    ¼
    0.06
    Granted
    0.06
    Activations Density 0.015%

    No Known Activations