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. 104412
    Prev
    Next
    INDEX
    Explanations

    hydro

    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
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tracking
    -0.06
    历
    -0.06
     لا
    -0.06
     Chambers
    -0.06
     hurry
    -0.06
    κτη
    -0.06
    wiki
    -0.06
     vous
    -0.06
     summarize
    -0.06
    	Date
    -0.06
    POSITIVE LOGITS
    .Α
    0.07
    atcher
    0.07
    ず
    0.07
    �
    0.07
    (ca
    0.07
    unal
    0.06
    ματα
    0.06
    Submission
    0.06
     어느
    0.06
     Def
    0.06
    Activations Density 0.017%

    No Known Activations