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. 21478
    Prev
    Next
    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash

    information related to colors and their associations, particularly in the context of flags.

    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
    lh
    -0.07
     العام
    -0.07
    timezone
    -0.07
    _align
    -0.06
    .Match
    -0.06
    _configure
    -0.06
    bbox
    -0.06
     Image
    -0.06
    -ro
    -0.06
    Keith
    -0.06
    POSITIVE LOGITS
     gent
    0.06
     cer
    0.06
     Malaysia
    0.06
     typing
    0.06
    §Ã
    0.06
    imming
    0.06
     condem
    0.06
     underst
    0.06
     accom
    0.06
     voy
    0.06
    Activations Density 0.089%

    No Known Activations