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. 87058
    Prev
    Next
    INDEX
    Explanations

    legal statutes

    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
     ())↵
    -0.08
     motivated
    -0.07
    ("-");↵
    -0.07
    Hits
    -0.06
     "\<
    -0.06
     усл
    -0.06
    >&
    -0.06
    __);↵
    -0.06
    initely
    -0.06
     revisit
    -0.06
    POSITIVE LOGITS
     attendance
    0.07
    .extract
    0.07
     CHUNK
    0.07
    )initWith
    0.06
     병
    0.06
     hyp
    0.06
    ophobia
    0.06
     pools
    0.06
    Rules
    0.06
    Scores
    0.06
    Activations Density 0.006%

    No Known Activations