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. 79581
    Prev
    Next
    INDEX
    Explanations

    recipes

    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
    gor
    -0.06
     inan
    -0.06
    acam
    -0.06
    Red
    -0.06
    евер
    -0.06
     travellers
    -0.06
                                                ↵
    -0.06
     Occ
    -0.06
     Bre
    -0.06
     bilin
    -0.06
    POSITIVE LOGITS
    教
    0.07
    [unit
    0.06
    .models
    0.06
     ﺍ
    0.06
    _NV
    0.06
    WSTR
    0.06
    ụp
    0.06
     kultur
    0.06
     Goku
    0.06
     Fairfield
    0.06
    Activations Density 0.094%

    No Known Activations