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. 122973
    Prev
    Next
    INDEX
    Explanations

    old

    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
    เฉ
    -0.07
    recent
    -0.07
    -ag
    -0.06
     ذکر
    -0.06
     mell
    -0.06
    pairs
    -0.06
    lamaz
    -0.06
     결과
    -0.06
     неправиль
    -0.06
     twenties
    -0.06
    POSITIVE LOGITS
    êm
    0.07
    ww
    0.06
     Case
    0.06
    (dtype
    0.06
     checks
    0.06
    (getResources
    0.06
     Veteran
    0.06
     Multi
    0.06
    .Comment
    0.06
     COOKIE
    0.06
    Activations Density 0.007%

    No Known Activations