© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109235
    Prev
    Next
    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash

    This neuron detects comment text in source code, especially lines introduced by comment markers (e.g. “//” and the following descriptive 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
     мед
    -0.07
    Tank
    -0.07
     Lazar
    -0.06
     Woody
    -0.06
     oprav
    -0.06
    /show
    -0.06
     Baz
    -0.06
     Ecc
    -0.06
    생활
    -0.06
    کتر
    -0.06
    POSITIVE LOGITS
    (utils
    0.07
     дня
    0.07
     amo
    0.06
    orses
    0.06
     Very
    0.06
    mise
    0.06
    {},
    0.06
    [arg
    0.06
    *',
    0.06
    .den
    0.06
    Activations Density 0.006%

    No Known Activations