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. 130325
    Prev
    Next
    INDEX
    Explanations

    general English language

    np_max-act · gemini-2.0-flash

    The neuron is tuned to detect numeric tokens—especially floating‐point (decimal) numbers—in the text.

    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
    amation
    -0.07
     professional
    -0.07
    profiles
    -0.06
    cards
    -0.06
    _REF
    -0.06
     brings
    -0.06
    ARB
    -0.06
    αρ
    -0.06
     glued
    -0.06
     affairs
    -0.06
    POSITIVE LOGITS
    ีม
    0.07
     giảm
    0.07
    _PROTOCOL
    0.06
     мол
    0.06
    개를
    0.06
     금액
    0.06
     frü
    0.06
    DropDown
    0.06
     한국
    0.06
     dříve
    0.06
    Activations Density 0.027%

    No Known Activations