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. 87054
    Prev
    Next
    INDEX
    Explanations

    days

    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
    $search
    -0.06
    ्वय
    -0.06
     TVs
    -0.06
    ань
    -0.06
    UpdatedAt
    -0.06
    cal
    -0.06
     stains
    -0.06
    father
    -0.06
     RTAL
    -0.06
    forth
    -0.05
    POSITIVE LOGITS
     referring
    0.07
     supernatural
    0.07
     Font
    0.06
    abyrin
    0.06
     Granted
    0.06
     Grund
    0.06
    acomment
    0.06
     Προ
    0.06
     PROCESS
    0.06
     ersten
    0.06
    Activations Density 0.003%

    No Known Activations