© 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. 11-RESID-POST-AA
    6. 78107
    Prev
    Next
    INDEX
    Explanations

    Nepal

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Uh
    -0.07
     Writes
    -0.06
     rủi
    -0.06
     knobs
    -0.06
     Jo
    -0.06
    леж
    -0.06
     homers
    -0.06
     Friedman
    -0.06
     Hu
    -0.06
     Terminator
    -0.06
    POSITIVE LOGITS
     Nepal
    0.08
     skeleton
    0.07
    ฐาน
    0.07
    .delivery
    0.06
    .Controller
    0.06
    líb
    0.06
    """↵↵↵
    0.06
    .RemoveAt
    0.06
    brtc
    0.06
     Cascade
    0.06
    Activations Density 0.008%

    No Known Activations