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. 80919
    Prev
    Next
    INDEX
    Explanations

    Chinese

    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
    on
    -0.07
     부탁
    -0.06
     okol
    -0.06
     attracting
    -0.06
     OA
    -0.06
     retract
    -0.06
    .area
    -0.06
    7
    -0.06
     exon
    -0.06
    .il
    -0.06
    POSITIVE LOGITS
     Chinese
    0.11
     Japanese
    0.10
    apanese
    0.09
    Chinese
    0.09
    	ts
    0.09
    ورش
    0.09
     chinese
    0.08
     Portuguese
    0.08
    inese
    0.08
    namese
    0.08
    Activations Density 0.014%

    No Known Activations