© 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
    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. 56726
    Prev
    Next
    INDEX
    Explanations

    circadian pacemakers

    np_max-act · gemini-2.0-flash

    information related to circadian rhythms and their regulatory mechanisms.

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

    This neuron is especially sensitive to mentions of the circadian “pacemaker” (and related circadian‐clock terminology).

    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
     týden
    -0.07
    ","",
    -0.06
     redd
    -0.06
    createQueryBuilder
    -0.06
    ++++++++++++++++++++++++++++++++
    -0.06
    .small
    -0.06
    ότητα
    -0.06
     جزء
    -0.06
    unn
    -0.06
    #######
    -0.06
    POSITIVE LOGITS
     svg
    0.08
    uild
    0.07
    lint
    0.07
    ')),↵
    0.07
    _actual
    0.07
     [];
    ↵
    0.07
     ard
    0.06
    .views
    0.06
    zh
    0.06
     внутріш
    0.06
    Activations Density 0.004%

    No Known Activations