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. 87094
    Prev
    Next
    INDEX
    Explanations

    questions or requests

    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
     Stokes
    -0.07
    -valu
    -0.06
    Min
    -0.06
    405
    -0.06
     damaging
    -0.06
    410
    -0.06
    amin
    -0.06
    	fprintf
    -0.06
     Shepherd
    -0.06
     Caf
    -0.06
    POSITIVE LOGITS
    도별
    0.07
    .ToUpper
    0.07
    ese
    0.06
    oloj
    0.06
     Socket
    0.06
     Spiral
    0.06
     eng
    0.06
    HE
    0.06
    姓名
    0.06
    -item
    0.06
    Activations Density 0.048%

    No Known Activations