© 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. 15-RESID-POST-AA
    6. 56156
    Prev
    Next
    INDEX
    Explanations

    .g

    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
     Fairy
    -0.07
     suffered
    -0.06
    線
    -0.06
    紹介
    -0.06
     نظری
    -0.06
     idea
    -0.06
     tanker
    -0.06
     glanced
    -0.06
     cathedral
    -0.06
    libc
    -0.06
    POSITIVE LOGITS
    'M
    0.08
    Bootstrap
    0.07
    _that
    0.07
    _android
    0.06
    -actions
    0.06
    _SETTING
    0.06
    ternal
    0.06
    teams
    0.06
    .t
    0.06
     रन
    0.06
    Activations Density 0.000%

    No Known Activations