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. 16211
    Prev
    Next
    INDEX
    Explanations

    rest of their life

    np_max-act · gemini-2.0-flash

    historical references to noble dynasties and their legacies.

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

    This neuron activates primarily on numeric tokens representing decimal or floating‐point values.

    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
    ωδ
    -0.07
    _Login
    -0.07
    說
    -0.07
    olist
    -0.06
    ้อน
    -0.06
    .Admin
    -0.06
    @class
    -0.06
    验
    -0.06
     从
    -0.06
    婷
    -0.06
    POSITIVE LOGITS
     carr
    0.07
     caveat
    0.07
    _but
    0.06
    �
    0.06
     را
    0.06
    finish
    0.06
     Cann
    0.06
     vou
    0.06
    (IM
    0.06
    /no
    0.06
    Activations Density 0.047%

    No Known Activations