© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 15789
    Prev
    Next
    INDEX
    Explanations

    web development/testing

    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
     jugador
    -0.07
     Vand
    -0.06
     LM
    -0.06
    :@"%@",
    -0.06
     Parallel
    -0.06
    .getBy
    -0.06
     Repository
    -0.06
    (java
    -0.06
    ,'#
    -0.06
     isolated
    -0.06
    POSITIVE LOGITS
    _EXTERN
    0.07
    術
    0.07
    Deployment
    0.07
    ----------------------------------------------------------------
    0.06
    efully
    0.06
    звичай
    0.06
    ************************************************************************
    0.06
     moż
    0.06
     société
    0.06
    ुआत
    0.06
    Activations Density 0.007%

    No Known Activations