© 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. 25222
    Prev
    Next
    INDEX
    Explanations

    setting variables in code

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting action‐oriented verbs (especially capitalized or initial identifiers like Set, Determine, Verify, make, collect, etc.) that usually begin function names or imperative comments.

    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
     Rivera
    -0.06
    Vari
    -0.06
     intValue
    -0.06
    -service
    -0.06
    _Frame
    -0.06
    ViewItem
    -0.06
    ‌پ
    -0.06
     Diaz
    -0.06
     bilm
    -0.06
    토
    -0.06
    POSITIVE LOGITS
    :item
    0.07
     platform
    0.06
     смот
    0.06
     punish
    0.06
    _DIFF
    0.06
     texts
    0.06
     dl
    0.06
     тим
    0.06
     centre
    0.06
     допомогою
    0.06
    Activations Density 0.033%

    No Known Activations