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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11205
    Prev
    Next
    INDEX
    Explanations

    code and technical information

    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
     dé
    -0.07
     yıllar
    -0.07
     mitigation
    -0.07
     evalu
    -0.07
    ció
    -0.06
     Benefit
    -0.06
    acional
    -0.06
    оці
    -0.06
    .mods
    -0.06
     vedle
    -0.06
    POSITIVE LOGITS
     pts
    0.07
    駆
    0.07
     fodder
    0.07
     medial
    0.06
     Listening
    0.06
    Listening
    0.06
    ヘ
    0.06
     Good
    0.06
    Right
    0.06
    pom
    0.06
    Activations Density 0.000%

    No Known Activations