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. 87076
    Prev
    Next
    INDEX
    Explanations

    ant

    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
    Operator
    -0.07
     Shin
    -0.06
    IN
    -0.06
     shin
    -0.06
    ватися
    -0.06
    Yet
    -0.06
    /tasks
    -0.06
    اشته
    -0.06
    呼ば
    -0.06
    _digest
    -0.06
    POSITIVE LOGITS
    (object
    0.07
    �
    0.07
    elijke
    0.07
    	require
    0.06
     Gio
    0.06
    гар
    0.06
     fmt
    0.06
    (Database
    0.06
     accurate
    0.06
     Apprent
    0.06
    Activations Density 0.245%

    No Known Activations