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. 10231
    Prev
    Next
    INDEX
    Explanations

    To

    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
     items
    -0.07
    起
    -0.06
     Pe
    -0.06
     demons
    -0.06
     armored
    -0.06
     Seminar
    -0.06
    ��
    -0.06
     Uh
    -0.06
     soru
    -0.06
    昭
    -0.06
    POSITIVE LOGITS
    CloseOperation
    0.08
    _BREAK
    0.07
    .FormBorderStyle
    0.07
    endency
    0.07
    �
    0.07
    \Facades
    0.07
     Westbrook
    0.07
    님이
    0.06
    ριά
    0.06
    GetComponent
    0.06
    Activations Density 0.000%

    No Known Activations