© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89643
    Prev
    Next
    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash

    The neuron detects Doxygen‐style documentation directives (e.g. backslash commands like “\file” or “\brief”) in code comments.

    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
     Snapchat
    -0.06
    [len
    -0.06
    Tweet
    -0.06
    .Prop
    -0.06
     Passage
    -0.06
     retina
    -0.06
    Imagen
    -0.06
     Lud
    -0.06
    щество
    -0.06
    VIEW
    -0.06
    POSITIVE LOGITS
    英雄
    0.07
     θ
    0.07
    			↵↵
    0.07
     Проф
    0.06
     pk
    0.06
     Strategy
    0.06
     Guests
    0.06
    	va
    0.06
     ‐
    0.06
    inqu
    0.06
    Activations Density 0.002%

    No Known Activations