Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RESID-POST-AA
    6. 93203
    Prev
    Next
    INDEX
    Explanations

    dough

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rif
    -0.07
     값
    -0.06
    적
    -0.06
     tỉnh
    -0.06
     expiration
    -0.06
     movie
    -0.06
    ic
    -0.06
     مورد
    -0.06
    لم
    -0.06
     celle
    -0.06
    POSITIVE LOGITS
     dough
    0.20
     Dough
    0.16
    ough
    0.08
    銀
    0.07
     धन
    0.07
     stadiums
    0.07
     Eisenhower
    0.07
     Mason
    0.06
    .MenuStrip
    0.06
    */↵
    0.06
    Activations Density 0.001%

    No Known Activations