© 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. 19-RESID-POST-AA
    11. 53649
    Prev
    Next
    INDEX
    Explanations

    Number sequences

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _UC
    -0.07
    Solar
    -0.07
    Menu
    -0.06
    View
    -0.06
     Gur
    -0.06
     Trey
    -0.06
    []{"
    -0.06
    /UI
    -0.06
    ynec
    -0.06
    ('|
    -0.06
    POSITIVE LOGITS
    -imm
    0.07
     تخصصی
    0.07
     rahat
    0.07
     Interracial
    0.07
    .fl
    0.06
     demonstrate
    0.06
     залеж
    0.06
     intelligent
    0.06
     legisl
    0.06
    });
    0.06
    Activations Density 0.029%

    No Known Activations