© 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. 125154
    Prev
    Next
    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash

    code-related discussions, particularly about warnings and syntax in programming.

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

    This neuron fires on mentions of programming‐language syntax elements—e.g. keywords like “struct” or punctuation terms such as “parentheses.”

    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
     retire
    -0.06
     Buddhism
    -0.06
     желуд
    -0.06
     tastes
    -0.06
     whisky
    -0.06
     container
    -0.06
     dét
    -0.06
     columna
    -0.06
    DDD
    -0.06
     commune
    -0.06
    POSITIVE LOGITS
    อกจาก
    0.07
     дій
    0.07
    .Success
    0.06
     componentDid
    0.06
     اینکه
    0.06
     (;;)
    0.06
     제
    0.06
    ดร
    0.06
    μιουργ
    0.06
     sag
    0.06
    Activations Density 0.052%

    No Known Activations