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. 111115
    Prev
    Next
    INDEX
    Explanations

    GUI code

    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
    _vis
    -0.07
     kinase
    -0.07
    (In
    -0.07
    ি
    -0.07
     Kanun
    -0.06
    ^K
    -0.06
    Win
    -0.06
    UGINS
    -0.06
    狐
    -0.06
     Shield
    -0.06
    POSITIVE LOGITS
     objc
    0.07
    urally
    0.07
    ypical
    0.07
    -menu
    0.07
    raph
    0.07
     transports
    0.07
    .Named
    0.07
    líč
    0.07
    (...
    0.06
    ancements
    0.06
    Activations Density 0.016%

    No Known Activations