© 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. 25347
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    code snippets related to handling asynchronous tasks in programming.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on conditional‐statement markers in code—especially the “if” keyword and its surrounding punctuation (parentheses and block tokens).

    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
     systematic
    -0.07
     Hong
    -0.06
    latin
    -0.06
     rehabilitation
    -0.06
     Device
    -0.06
    ffi
    -0.06
     Georges
    -0.06
    ňuje
    -0.06
    .NODE
    -0.06
     defaultMessage
    -0.06
    POSITIVE LOGITS
    kening
    0.07
     sper
    0.07
    جن
    0.07
     až
    0.06
     l
    0.06
    =session
    0.06
    =path
    0.06
     scripted
    0.06
    graf
    0.06
    *R
    0.06
    Activations Density 0.051%

    No Known Activations