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. 110922
    Prev
    Next
    INDEX
    Explanations

    scientific/medical texts

    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
    _response
    -0.07
    utr
    -0.07
    IMATION
    -0.07
     collaboration
    -0.07
     airs
    -0.07
    WI
    -0.06
     unable
    -0.06
     Communication
    -0.06
    OUGH
    -0.06
    REE
    -0.06
    POSITIVE LOGITS
    ượu
    0.07
    edii
    0.07
     propane
    0.07
     keyst
    0.06
     noexcept
    0.06
    �
    0.06
     活
    0.06
     منابع
    0.06
    readcr
    0.06
     Angelo
    0.06
    Activations Density 0.291%

    No Known Activations