Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 125515
    Prev
    Next
    INDEX
    Explanations

    computer programming

    np_max-act · gemini-2.0-flash

    This neuron fires on discussion of an unintended trailing semicolon (a “suffix”) in code, e.g. the stray `;` after a `while` statement.

    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
    rops
    -0.07
     화
    -0.07
     Modal
    -0.07
    Items
    -0.07
     Layout
    -0.06
    wp
    -0.06
    `.`
    -0.06
     škol
    -0.06
    ongoose
    -0.06
    92
    -0.06
    POSITIVE LOGITS
    _reader
    0.07
    ujet
    0.07
     tiên
    0.06
    럽
    0.06
    (pre
    0.06
     dangling
    0.06
     vere
    0.06
    venient
    0.06
    (mod
    0.06
    [section
    0.06
    Activations Density 0.074%

    No Known Activations