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. 87085
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    $$$$
    -0.07
    ("$
    -0.07
    แรง
    -0.06
    ares
    -0.06
    aldo
    -0.06
    \$
    -0.06
    /users
    -0.06
     LTC
    -0.06
    출장샵
    -0.06
    .delivery
    -0.06
    POSITIVE LOGITS
    _AUT
    0.07
    ={}↵
    0.06
    mallow
    0.06
    ===========↵
    0.06
    ,d
    0.06
    NAMESPACE
    0.06
    addAll
    0.06
    	output
    0.06
     Concrete
    0.06
     commune
    0.06
    Activations Density 0.002%

    No Known Activations