© 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. 19-RESID-POST-AA
    11. 9510
    Prev
    Next
    INDEX
    Explanations

    characters

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lông
    -0.07
    orie
    -0.07
     observers
    -0.06
     thinker
    -0.06
    ыт
    -0.06
    90
    -0.06
    ido
    -0.06
     lorsque
    -0.06
    Fred
    -0.06
     tried
    -0.06
    POSITIVE LOGITS
    adolu
    0.07
    文件
    0.07
    favicon
    0.06
    .unlink
    0.06
    usat
    0.06
    obili
    0.06
    /opt
    0.06
    asaki
    0.06
    γμα
    0.06
     çay
    0.06
    Activations Density 0.104%

    No Known Activations