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. 86334
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash

    The neuron fires on words naming kitchen‐ and cooking-related items or actions (e.g. “kitchen,” “cereal,” “cornflakes,” “emerged [from the kitchen]”).

    oai_token-act-pair · o4-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
    $form
    -0.07
    _sys
    -0.06
    (DEBUG
    -0.06
     {?
    -0.06
    株
    -0.06
    Displays
    -0.06
     Thực
    -0.06
     آذ
    -0.06
     ACTION
    -0.06
    hq
    -0.06
    POSITIVE LOGITS
    浅
    0.06
     üzerinden
    0.06
     comentarios
    0.06
     آمد
    0.06
     पक
    0.06
    _fmt
    0.06
     premiered
    0.06
     underestimated
    0.06
     Railroad
    0.05
     contradiction
    0.05
    Activations Density 0.043%

    No Known Activations