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. 80697
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ()});↵
    -0.08
    Builders
    -0.07
    Friends
    -0.07
    _DOMAIN
    -0.06
    pressor
    -0.06
     IconData
    -0.06
    ์พ
    -0.06
    Fish
    -0.06
    .fold
    -0.06
     pv
    -0.06
    POSITIVE LOGITS
    ■■
    0.07
     COPYRIGHT
    0.07
     			
    0.06
     Spike
    0.06
    Return
    0.06
     ↵↵↵↵
    0.06
     сбор
    0.06
     Deliver
    0.06
    同じ
    0.06
    _url
    0.06
    Activations Density 0.152%

    No Known Activations