© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55823
    Prev
    Next
    INDEX
    Explanations

    exclamation point

    np_max-act · gemini-2.0-flash

    The neuron activates on the ‘!’ operator in C/C++ preprocessor conditionals (e.g. “#if !defined(…)”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical terms and components related to programming and software development.

    oai_token-act-pair · gpt-4o-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
     Inflate
    -0.07
    едагог
    -0.07
     ')';↵
    -0.07
    .af
    -0.06
    щих
    -0.06
    ));↵↵↵
    -0.06
     یافت
    -0.06
    uropean
    -0.06
    CLEAR
    -0.06
     došlo
    -0.06
    POSITIVE LOGITS
    =a
    0.06
     Maya
    0.06
     minY
    0.06
     period
    0.06
     abandon
    0.06
     couldn
    0.06
     edm
    0.06
    �
    0.06
    iclass
    0.05
    수가
    0.05
    Activations Density 0.002%

    No Known Activations