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. 87055
    Prev
    Next
    INDEX
    Explanations

    nearest number

    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
     resemble
    -0.07
     Amar
    -0.07
    conciliation
    -0.07
    *T
    -0.07
     Hal
    -0.06
    ictim
    -0.06
    -ref
    -0.06
     onun
    -0.06
     आकर
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    .useState
    0.07
     बय
    0.07
    :'',↵
    0.06
     copying
    0.06
    deme
    0.06
     xy
    0.06
     Sigma
    0.06
     sponge
    0.06
    localhost
    0.06
    .action
    0.06
    Activations Density 0.001%

    No Known Activations