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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21218
    Prev
    Next
    INDEX
    Explanations

    legal

    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
    iken
    -0.08
    ,type
    -0.07
    ometer
    -0.06
     preserving
    -0.06
    _null
    -0.06
    Empresa
    -0.06
    ==
    -0.06
    argest
    -0.06
    _out
    -0.06
    258
    -0.06
    POSITIVE LOGITS
     pratic
    0.07
     });
    ↵
    0.07
     trắng
    0.07
     Clare
    0.06
     rencontrer
    0.06
     keynote
    0.06
    .textAlignment
    0.06
    зація
    0.06
    ellt
    0.06
     predatory
    0.06
    Activations Density 0.112%

    No Known Activations