© 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. 79899
    Prev
    Next
    INDEX
    Explanations

    preg

    np_max-act · gemini-2.0-flash

    code snippets related to string manipulation using regular expressions in PHP.

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

    The neuron activates on mentions of PHP’s regex‐replacement function calls—specifically the “preg_replace” token.

    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
     Independence
    -0.07
     whisky
    -0.07
     Roberto
    -0.07
     HDC
    -0.06
     reckless
    -0.06
     robbery
    -0.06
    ruits
    -0.06
    :::::::::
    -0.06
     XOR
    -0.06
     Scot
    -0.06
    POSITIVE LOGITS
     khuyến
    0.08
    ाइम
    0.07
     συμβ
    0.07
     sidelined
    0.07
     تمر
    0.06
    preg
    0.06
     pilots
    0.06
     vyd
    0.06
    َج
    0.06
    อาช
    0.06
    Activations Density 0.001%

    No Known Activations