© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 104963
    Prev
    Next
    INDEX
    Explanations

    medical operations

    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
    Sol
    -0.07
     Gor
    -0.07
    Crop
    -0.07
     Thai
    -0.07
     contracting
    -0.07
    -process
    -0.06
    -part
    -0.06
    Crypt
    -0.06
    .best
    -0.06
    Fish
    -0.06
    POSITIVE LOGITS
     ремон
    0.07
    geber
    0.06
     �
    0.06
    .number
    0.06
    NewItem
    0.06
    enal
    0.06
    まで
    0.06
     تنظیم
    0.06
     INCIDENT
    0.06
    ิทยาล
    0.06
    Activations Density 0.026%

    No Known Activations