Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 30327
    Prev
    Next
    INDEX
    Explanations

    Pin

    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
    feel
    -0.07
    051
    -0.07
     Tipo
    -0.06
    ]}</
    -0.06
    Honestly
    -0.06
     ↵  ↵
    -0.06
    todos
    -0.06
    üp
    -0.06
    ?");↵
    -0.06
    ντ
    -0.06
    POSITIVE LOGITS
    _approved
    0.07
    .dynamic
    0.07
     rağmen
    0.06
     COURT
    0.06
    (outputs
    0.06
    .Display
    0.06
    (ExpectedConditions
    0.06
     Voltage
    0.06
    Animator
    0.06
    レビ
    0.06
    Activations Density 0.263%

    No Known Activations