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. 15-RESID-POST-AA
    6. 111304
    Prev
    Next
    INDEX
    Explanations

    mitigate

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diplomats
    -0.07
     Haus
    -0.07
     confess
    -0.07
     Burada
    -0.06
     اص
    -0.06
     religious
    -0.06
     opponents
    -0.06
     compan
    -0.06
    Express
    -0.06
    奏
    -0.06
    POSITIVE LOGITS
     mitigate
    0.09
     mitig
    0.07
     Reduce
    0.06
    GLfloat
    0.06
    Kat
    0.06
    ेय
    0.06
    .removeItem
    0.06
    _NV
    0.06
    韓
    0.06
     кого
    0.06
    Activations Density 0.009%

    No Known Activations