© 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. 73656
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron fires on conditional‐compilation and reader‐conditional markers (e.g. “endif” or Clojure’s reader‐conditional forms like `#?`/`#:blah`), i.e. tokens that close or denote conditional blocks.

    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
    ий
    -0.07
     plants
    -0.06
    jší
    -0.06
     Eaton
    -0.06
    marginLeft
    -0.06
    .cond
    -0.06
    tracked
    -0.06
     DX
    -0.06
     plant
    -0.06
    _scope
    -0.06
    POSITIVE LOGITS
    .STATE
    0.07
     Advisory
    0.07
    getApplication
    0.06
    .getColumn
    0.06
     frowned
    0.06
    (optional
    0.06
    Recommended
    0.06
    Jak
    0.06
     cra
    0.06
     //<
    0.06
    Activations Density 0.096%

    No Known Activations