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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 15-RESID-POST-AA
    6. 74665
    Prev
    Next
    INDEX
    Explanations

    .h

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -stack
    -0.06
    아이
    -0.06
    _ci
    -0.06
     spo
    -0.06
    inactive
    -0.06
     interpersonal
    -0.06
    _STOCK
    -0.06
     esports
    -0.06
    }}</
    -0.06
    iosk
    -0.06
    POSITIVE LOGITS
    Gateway
    0.07
     Philippe
    0.07
    TX
    0.07
    	pstmt
    0.06
    :H
    0.06
    Methods
    0.06
    -Headers
    0.06
     Kirk
    0.06
    Framework
    0.06
    ays
    0.06
    Activations Density 0.002%

    No Known Activations