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. 86262
    Prev
    Next
    INDEX
    Explanations

    preparation and synthesis

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of the word “synthesis” in the chemical‐process descriptions.

    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
    /*------------------------------------------------
    -0.09
     igen
    -0.06
    気に入
    -0.06
    Matrix
    -0.06
    .widget
    -0.06
    .graph
    -0.06
    	stage
    -0.06
     workshops
    -0.06
    \Entity
    -0.06
    zek
    -0.06
    POSITIVE LOGITS
    ibly
    0.06
    Estimated
    0.06
    ','.
    0.06
     presumably
    0.06
     vip
    0.06
    ENGINE
    0.06
    ?↵
    0.06
    春
    0.06
     IMS
    0.06
    asthan
    0.06
    Activations Density 0.017%

    No Known Activations