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. 11-RESID-POST-AA
    6. 104237
    Prev
    Next
    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash

    functions and code structures related to mathematical operations and comparisons.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _PIXEL
    -0.07
    mys
    -0.06
    оз
    -0.06
     riêng
    -0.06
     الجز
    -0.06
    -animation
    -0.06
    _invite
    -0.06
    κης
    -0.06
     kitten
    -0.06
    ếu
    -0.06
    POSITIVE LOGITS
    .samples
    0.07
    ênh
    0.07
     vám
    0.06
    .Local
    0.06
    itte
    0.06
     cough
    0.06
     imaginative
    0.06
     Yamaha
    0.06
     Mozilla
    0.06
    spiel
    0.06
    Activations Density 0.009%

    No Known Activations