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. 87096
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     cake
    -0.07
     PDF
    -0.07
     Wifi
    -0.07
    Canvas
    -0.06
    invisible
    -0.06
     き
    -0.06
     Wikispecies
    -0.06
     μπορού
    -0.06
     сосед
    -0.06
    owl
    -0.06
    POSITIVE LOGITS
    .ManyToMany
    0.07
    .memory
    0.07
    -get
    0.06
    patial
    0.06
     Стар
    0.06
    iram
    0.06
    ailles
    0.06
     Injury
    0.06
    ‘
    0.06
    arbeit
    0.06
    Activations Density 0.050%

    No Known Activations