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. 11-RESID-POST-AA
    6. 101226
    Prev
    Next
    INDEX
    Explanations

    web pages and user actions

    np_max-act · gemini-2.0-flash

    conversations or interactions in various scenarios.

    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
    uars
    -0.07
    omez
    -0.06
     Leia
    -0.06
    $v
    -0.06
    ONA
    -0.06
    暖
    -0.06
    ีฬา
    -0.06
    Headers
    -0.06
    _makeConstraints
    -0.06
     Vy
    -0.06
    POSITIVE LOGITS
     monkeys
    0.07
    chet
    0.06
    ino
    0.06
     Statistical
    0.06
    历史
    0.06
     attended
    0.06
    llib
    0.06
     Identifier
    0.06
    tridge
    0.06
     nét
    0.06
    Activations Density 0.026%

    No Known Activations