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

    Neuronpedia

    APICircuit 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. 54102
    Prev
    Next
    INDEX
    Explanations

    colon/dash

    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
     Ма
    -0.07
    .ReadAsStringAsync
    -0.07
    -min
    -0.06
     Cristiano
    -0.06
    .findById
    -0.06
    .Un
    -0.06
    'A
    -0.06
    '-
    -0.06
     мед
    -0.06
    =").
    -0.06
    POSITIVE LOGITS
     costs
    0.07
    credible
    0.07
     Vegetable
    0.06
     baseline
    0.06
    _rect
    0.06
     Jersey
    0.06
    运动
    0.06
     yOffset
    0.06
    iała
    0.06
     مهم
    0.06
    Activations Density 0.003%

    No Known Activations