© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 692
    Prev
    Next
    INDEX
    Explanations

    bed/bedtime

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of sleep or going to bed (e.g. “sleep,” “bed,” “bedtime”).

    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
    common
    -0.06
    iao
    -0.06
    ANNER
    -0.06
    /common
    -0.06
    isEqualTo
    -0.06
    (factor
    -0.06
    ArgumentException
    -0.06
     mø
    -0.06
    >_
    -0.06
    ướ
    -0.06
    POSITIVE LOGITS
     bedtime
    0.12
    UTC
    0.07
    аб
    0.07
     Todo
    0.06
    лі
    0.06
    odal
    0.06
    .Html
    0.06
    lid
    0.06
     SHE
    0.06
     SPE
    0.06
    Activations Density 0.003%

    No Known Activations