© 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. 128776
    Prev
    Next
    INDEX
    Explanations

    _VER

    np_max-act · gemini-2.0-flash

    This neuron detects numeric version checks in C/C++ preprocessor conditionals (e.g., comparisons involving _MSC_VER or similar macros).

    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
    ,img
    -0.08
    olf
    -0.07
    ーツ
    -0.07
    	fire
    -0.07
     SDL
    -0.06
    _episode
    -0.06
    _THRESH
    -0.06
    φό
    -0.06
    RAND
    -0.06
    blood
    -0.06
    POSITIVE LOGITS
     그냥
    0.07
    ayın
    0.07
     ocor
    0.06
     Denise
    0.06
    	sp
    0.06
     sensitive
    0.06
     deductions
    0.06
     tür
    0.06
     Sır
    0.06
     кош
    0.06
    Activations Density 0.002%

    No Known Activations