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

    Neuronpedia

    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. 7640
    Prev
    Next
    INDEX
    Explanations

    cues, triggers, reminders

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of external cues or triggers (e.g. “cue,” “triggered,” “stimuli,” “urge”) that provoke craving or urge responses.

    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
    岳
    -0.07
    -zero
    -0.07
    卡
    -0.06
     buffer
    -0.06
    フェ
    -0.06
    vý
    -0.06
     alpha
    -0.06
     통
    -0.06
    free
    -0.06
    闭
    -0.06
    POSITIVE LOGITS
    /Foundation
    0.07
    inate
    0.07
     onCancelled
    0.07
     初始化
    0.06
    _INTEGER
    0.06
    /mm
    0.06
    _ing
    0.06
     GTX
    0.06
     Tes
    0.06
    %;">
    0.06
    Activations Density 0.027%

    No Known Activations