© 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. 7972
    Prev
    Next
    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash

    The neuron activates on explanatory syntax‐definition phrases (e.g. “The syntax for the … function is …”), marking lines that introduce a function’s usage format.

    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
    196
    -0.07
    “At
    -0.07
     replacements
    -0.06
    _HINT
    -0.06
    xBB
    -0.06
     Action
    -0.06
    199
    -0.06
    (cc
    -0.06
     España
    -0.06
     Darling
    -0.06
    POSITIVE LOGITS
    ดย
    0.07
     دفتر
    0.06
    -describedby
    0.06
     seriously
    0.06
    γα
    0.06
     úřad
    0.06
     вищ
    0.06
    .tech
    0.06
    izzlies
    0.06
    교육
    0.06
    Activations Density 0.026%

    No Known Activations