Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 123178
    Prev
    Next
    INDEX
    Explanations

    App

    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
     κύ
    -0.08
     unavoid
    -0.07
    iž
    -0.07
    72
    -0.07
    boundary
    -0.07
    ляли
    -0.07
    ovíd
    -0.07
     hâl
    -0.07
    jug
    -0.07
    üre
    -0.07
    POSITIVE LOGITS
     app
    0.12
     App
    0.09
    apps
    0.09
    App
    0.08
    app
    0.08
    /App
    0.08
    A
    0.08
     pack
    0.08
    /apps
    0.08
    APP
    0.08
    Activations Density 0.050%

    No Known Activations