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. 86143
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    chemical compounds used in various industrial applications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on chemical compound identifiers or abbreviations (e.g. sequences of uppercase letters and numbers like “DCPA”).

    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
    جو
    -0.07
    تبه
    -0.06
    Programming
    -0.06
    560
    -0.06
    izing
    -0.06
    Qt
    -0.06
     Εν
    -0.06
    ила
    -0.06
     having
    -0.06
     employer
    -0.06
    POSITIVE LOGITS
     parachute
    0.07
     comentarios
    0.06
     ض
    0.06
     inferred
    0.06
     …↵
    0.06
     undue
    0.06
    _extractor
    0.06
    GridColumn
    0.06
    .sprites
    0.06
     SCH
    0.06
    Activations Density 0.014%

    No Known Activations