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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 38402
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron detects relative time‐ago expressions and related code or comments (e.g. “X minutes ago,” “about 1 day ago,” “fuzzy timestamps,” humanize/duration/ago functions).

    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
    BUG
    -0.07
    IPC
    -0.07
     Coconut
    -0.06
    >Contact
    -0.06
    	cnt
    -0.06
    -button
    -0.06
    gram
    -0.06
     quotation
    -0.06
     kInstruction
    -0.06
     quotations
    -0.06
    POSITIVE LOGITS
     Cowboy
    0.07
    आर
    0.06
     دری
    0.06
     Türkiye
    0.06
    ених
    0.06
    podob
    0.06
     onder
    0.06
    /mod
    0.06
     associative
    0.06
     agua
    0.06
    Activations Density 0.010%

    No Known Activations