© 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
    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. 30601
    Prev
    Next
    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that are part of date or time expressions (e.g., months, days, years, and words like “until,” “expiring,” “ending”).

    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
    '])){
↵
    -0.06
    입
    -0.06
    Labour
    -0.06
    ISTRIBUT
    -0.06
    {})↵
    -0.06
     dormant
    -0.06
     Hilfe
    -0.06
    euillez
    -0.06
    &)↵
    -0.06
     "==
    -0.06
    POSITIVE LOGITS
    ัญญ
    0.07
    祭
    0.06
    _messages
    0.06
    [source
    0.06
     जल
    0.06
    cci
    0.06
     TIMESTAMP
    0.06
    -breaking
    0.06
    _nombre
    0.06
    ểm
    0.06
    Activations Density 0.016%

    No Known Activations