Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78299
    Prev
    Next
    INDEX
    Explanations

    dropdown menus and UI

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (rect
    -0.07
     Manitoba
    -0.07
    inem
    -0.06
    IColor
    -0.06
     McGregor
    -0.06
    Metrics
    -0.06
    shift
    -0.06
    Kansas
    -0.06
    (Expression
    -0.06
    Clusters
    -0.06
    POSITIVE LOGITS
     крови
    0.07
     dubna
    0.07
    months
    0.06
     Sit
    0.06
    客
    0.06
     �
    0.06
    IMIT
    0.06
    bra
    0.06
    .avi
    0.06
    .Sql
    0.06
    Activations Density 0.015%

    No Known Activations