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. 130478
    Prev
    Next
    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash

    This neuron fires on imperative code tokens—i.e. function names or command verbs in code examples.

    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
     дея
    -0.06
     Wel
    -0.06
     Bucc
    -0.06
    ैल
    -0.06
    καν
    -0.06
     partir
    -0.06
     одного
    -0.06
    스는
    -0.06
    iego
    -0.06
    ीश
    -0.06
    POSITIVE LOGITS
     philosophical
    0.08
     if
    0.07
    菌
    0.07
     Licence
    0.07
     bondage
    0.07
     Constraints
    0.06
     hospitality
    0.06
    ература
    0.06
    )row
    0.06
    .decorators
    0.06
    Activations Density 0.027%

    No Known Activations