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. 130501
    Prev
    Next
    INDEX
    Explanations

    API-related code

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting software version numbers (numeric tokens) in title strings (e.g. the “2.8.0” or “3.4.0” parts before “API”).

    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
    ouchers
    -0.07
    threads
    -0.07
    _INSTANCE
    -0.07
     Loren
    -0.06
    swire
    -0.06
     Gotham
    -0.06
    orrent
    -0.06
    \Modules
    -0.06
    ampaign
    -0.06
    ERVICE
    -0.06
    POSITIVE LOGITS
     ao
    0.07
    ogonal
    0.07
    専
    0.07
    ::↵↵
    0.07
    ...\
    0.06
    okoj
    0.06
     slit
    0.06
    情况
    0.06
     OTA
    0.06
    갈
    0.06
    Activations Density 0.012%

    No Known Activations