© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7308
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron fires on parameter names (e.g. “target,” “url,” “http,” “other”) within code documentation, identifying tokens that label function/method arguments.

    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
    "Some
    -0.07
     grilled
    -0.07
    "To
    -0.07
    ottie
    -0.06
    	mc
    -0.06
    福利
    -0.06
     Jonah
    -0.06
     affid
    -0.06
     bx
    -0.06
     yanı
    -0.06
    POSITIVE LOGITS
    ีน
    0.07
    ////////////////////////////////////////////////////////////////////////////////↵
    0.06
    _limit
    0.06
     Hurricane
    0.06
     lw
    0.06
    题
    0.06
    _ut
    0.06
    ieces
    0.06
     Amid
    0.06
     Forward
    0.06
    Activations Density 0.015%

    No Known Activations