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. 7-RESID-POST-AA
    6. 49537
    Prev
    Next
    INDEX
    Explanations

    canvas size in coding

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jones
    -0.07
    'utilisateur
    -0.07
     PLAYER
    -0.07
     SDS
    -0.06
     Все
    -0.06
    공지
    -0.06
    onen
    -0.06
     Kath
    -0.06
    \-
    -0.06
    είς
    -0.06
    POSITIVE LOGITS
    ?
    0.07
    )[
    0.06
     інших
    0.06
     umbrella
    0.06
     sperma
    0.06
    車
    0.06
    ać
    0.06
    grep
    0.06
    _tp
    0.06
    _verify
    0.06
    Activations Density 0.008%

    No Known Activations