© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 56543
    Prev
    Next
    INDEX
    Explanations

    finding someone

    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
     bureauc
    -0.08
    (pthread
    -0.07
     rizik
    -0.07
    =true
    -0.07
     textu
    -0.06
    wner
    -0.06
     Jeg
    -0.06
    .dataSource
    -0.06
    imité
    -0.06
     écrit
    -0.06
    POSITIVE LOGITS
     Treat
    0.07
    $conn
    0.06
    (datetime
    0.06
    Eat
    0.06
    ｯ
    0.06
     con
    0.06
    tickets
    0.06
    -solid
    0.06
     Channel
    0.06
     ут
    0.06
    Activations Density 0.001%

    No Known Activations