© 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. 38630
    Prev
    Next
    INDEX
    Explanations

    Time calculations

    np_max-act · gemini-2.0-flash

    This neuron fires on the numeric hour (and following minute tokens) of the second (later) time expression in “how many minutes between … and …” or “what is … after/before …” questions, effectively marking the end time.

    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
    ,A
    -0.07
     computer
    -0.06
    eman
    -0.06
    然
    -0.06
    ign
    -0.06
    Stuff
    -0.06
    มา
    -0.06
    izin
    -0.06
     Chick
    -0.06
    ,P
    -0.06
    POSITIVE LOGITS
     ()
    0.07
    _sha
    0.07
    имв
    0.06
    depends
    0.06
     Nut
    0.06
     Vũ
    0.06
    seq
    0.06
    llib
    0.06
     объяс
    0.06
    .CON
    0.06
    Activations Density 0.002%

    No Known Activations