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. 85981
    Prev
    Next
    INDEX
    Explanations

    /java

    np_max-act · gemini-2.0-flash

    This neuron fires on multiline code excerpts (blocks of programming code) within 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
     Lol
    -0.06
     повин
    -0.06
     продолж
    -0.06
     subsystem
    -0.06
     Укра
    -0.06
    _CNT
    -0.06
    vat
    -0.06
     ráno
    -0.06
     kdo
    -0.06
     esto
    -0.06
    POSITIVE LOGITS
     highlights
    0.07
    <_
    0.06
     setC
    0.06
    <unsigned
    0.06
    频
    0.06
    _APPS
    0.06
    (bean
    0.06
     valueForKey
    0.06
    ,unsigned
    0.06
    =json
    0.06
    Activations Density 0.003%

    No Known Activations