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. 87115
    Prev
    Next
    INDEX
    Explanations

    Consequences/Risks

    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
    .Message
    -0.07
     cleaned
    -0.07
     Valk
    -0.06
    icrosoft
    -0.06
    /logging
    -0.06
     homophobic
    -0.06
     buffered
    -0.06
     skirts
    -0.06
    üt
    -0.06
    Amazon
    -0.06
    POSITIVE LOGITS
     плод
    0.07
    (dx
    0.07
     precipitation
    0.07
     diseñ
    0.06
     employ
    0.06
     Tow
    0.06
     ilk
    0.06
     Edison
    0.06
    @endsection
    0.06
    .nick
    0.06
    Activations Density 0.058%

    No Known Activations