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. 87089
    Prev
    Next
    INDEX
    Explanations

    scientific writing

    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
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unami
    -0.06
    ูต
    -0.06
    law
    -0.06
    Twenty
    -0.06
    الث
    -0.06
    었다
    -0.05
    Syn
    -0.05
    575
    -0.05
     west
    -0.05
    ).\
    -0.05
    POSITIVE LOGITS
     Witnesses
    0.07
     maxlen
    0.07
    ='/
    0.07
    /demo
    0.07
    _SAVE
    0.06
     antidepress
    0.06
     preprocess
    0.06
    ाइड
    0.06
    loggedIn
    0.06
     Rodrig
    0.06
    Activations Density 0.132%

    No Known Activations