© 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. 129602
    Prev
    Next
    INDEX
    Explanations

    F

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of low‐level atomic synchronization or memory‐operation primitives (e.g., test‐and‐set, compare‐and‐swap).

    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
    bum
    -0.07
    urrencies
    -0.07
    政策
    -0.07
    columns
    -0.06
    aw
    -0.06
    زر
    -0.06
    (food
    -0.06
    _four
    -0.06
     ew
    -0.06
     χρη
    -0.06
    POSITIVE LOGITS
    OMIC
    0.06
    _Date
    0.06
    ocio
    0.06
    .ready
    0.06
     breadcrumbs
    0.06
     Marxist
    0.06
    $('
    0.06
    (Time
    0.05
    GTK
    0.05
    _DIRECTION
    0.05
    Activations Density 0.169%

    No Known Activations