© 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. 23-RESID-POST-AA
    11. 7708
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Casinos
    -0.07
     Lawrence
    -0.06
     Mary
    -0.06
    oid
    -0.06
    щают
    -0.06
     později
    -0.06
     Coins
    -0.06
     Doming
    -0.06
     Boulevard
    -0.06
     makers
    -0.06
    POSITIVE LOGITS
    ERSIST
    0.07
    에서의
    0.07
    internal
    0.07
    _descriptor
    0.07
     gener
    0.06
    .gamma
    0.06
     descriptive
    0.06
    .GetCurrent
    0.06
     Tiếng
    0.06
    overall
    0.06
    Activations Density 0.019%

    No Known Activations