© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91945
    Prev
    Next
    INDEX
    Explanations

    Spring/Java code

    np_max-act · gemini-2.0-flash

    The neuron principally picks up on code indentation and formatting whitespace tokens (e.g. the leading spaces/tabs before Java keywords and annotations).

    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
     semantics
    -0.07
    Attachment
    -0.06
     طرف
    -0.06
    찮
    -0.06
    monton
    -0.06
    elled
    -0.06
     lên
    -0.06
     MMA
    -0.06
    اس
    -0.06
     〈
    -0.06
    POSITIVE LOGITS
    .after
    0.06
    iland
    0.06
    _PROF
    0.06
    只要
    0.06
    <Expression
    0.06
    urence
    0.06
    _claim
    0.06
    />\
    0.06
    difference
    0.06
    ijkstra
    0.06
    Activations Density 0.002%

    No Known Activations