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. 87078
    Prev
    Next
    INDEX
    Explanations

    Code/data snippets

    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
    ิช
    -0.07
    .CheckedChanged
    -0.06
    .HasPrefix
    -0.06
     mish
    -0.06
    ンデ
    -0.06
    AINS
    -0.06
    peated
    -0.06
    ampp
    -0.06
    ’hui
    -0.06
     AccessToken
    -0.05
    POSITIVE LOGITS
    通常
    0.07
    Bg
    0.07
    .sol
    0.07
     شمالی
    0.06
     sympt
    0.06
    平均
    0.06
    ξ
    0.06
     �
    0.06
    (elem
    0.06
     wol
    0.06
    Activations Density 0.006%

    No Known Activations