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. 111121
    Prev
    Next
    INDEX
    Explanations

    same

    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
     रस
    -0.07
    "};↵
    -0.07
    Warnings
    -0.07
    HO
    -0.06
     nil
    -0.06
    智能
    -0.06
     hx
    -0.06
    /downloads
    -0.06
    .='
    -0.06
        	↵
    -0.06
    POSITIVE LOGITS
     gps
    0.07
    料
    0.07
     Beetle
    0.07
    (company
    0.06
    Registration
    0.06
    _Type
    0.06
    Via
    0.06
    _ME
    0.06
    èles
    0.06
     millet
    0.06
    Activations Density 0.004%

    No Known Activations