© 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. 59076
    Prev
    Next
    INDEX
    Explanations

    out

    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
    _dialog
    -0.07
     baik
    -0.06
     United
    -0.06
    _puts
    -0.06
     μεταξύ
    -0.06
    父
    -0.06
    าณ
    -0.06
    نتی
    -0.06
    [parent
    -0.06
     saddened
    -0.06
    POSITIVE LOGITS
     presup
    0.07
     useSelector
    0.06
     �
    0.06
    .forEach
    0.06
    .payload
    0.06
     وضعیت
    0.06
     squirt
    0.06
     OUT
    0.06
     plut
    0.06
    ,out
    0.06
    Activations Density 0.005%

    No Known Activations