© 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. 3-RESID-POST-AA
    6. 123092
    Prev
    Next
    INDEX
    Explanations

    config

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CRYPT
    -0.06
    _TB
    -0.06
    чает
    -0.06
    ै.
    -0.06
    hasOne
    -0.06
    (matches
    -0.06
    íveis
    -0.06
     příliš
    -0.06
    ρυ
    -0.06
     stanov
    -0.06
    POSITIVE LOGITS
    CONFIG
    0.18
    під
    0.08
     cabin
    0.07
     excellence
    0.06
    .MAIN
    0.06
    )";
    ↵
    0.06
    ин
    0.06
    callee
    0.06
    }\"
    0.06
    (ExpectedConditions
    0.06
    Activations Density 0.002%

    No Known Activations