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. 81266
    Prev
    Next
    INDEX
    Explanations

    conn

    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_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
     MUSIC
    -0.07
    films
    -0.07
    ELEMENT
    -0.07
    _boundary
    -0.06
    шее
    -0.06
     wird
    -0.06
     tumblr
    -0.06
     lab
    -0.06
    alysis
    -0.06
     neurons
    -0.06
    POSITIVE LOGITS
    upyter
    0.07
    _inp
    0.07
    .keras
    0.07
    รณ
    0.07
     Polit
    0.07
    _pago
    0.07
    .$.
    0.06
    ilent
    0.06
    =str
    0.06
    ूच
    0.06
    Activations Density 0.006%

    No Known Activations