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. 81233
    Prev
    Next
    INDEX
    Explanations

    oven

    np_max-act · gemini-2.0-flash

    items and features related to kitchen appliances, specifically ovens.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
     birds
    -0.07
     asset
    -0.07
    fluence
    -0.07
     linked
    -0.07
    Tracks
    -0.07
    leaders
    -0.06
     tick
    -0.06
    .TabPage
    -0.06
     left
    -0.06
    :left
    -0.06
    POSITIVE LOGITS
     oven
    0.13
     Oven
    0.11
     furnace
    0.09
     stove
    0.08
    (Environment
    0.07
    CRT
    0.07
     uneven
    0.07
     JVM
    0.06
     SQLITE
    0.06
    (MigrationBuilder
    0.06
    Activations Density 0.005%

    No Known Activations