© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42561
    Prev
    Next
    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash

    This neuron activates on the literal “<” token (e.g. the opening angle bracket in include directives), so it’s detecting occurrences of “<” in code.

    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
    ुपय
    -0.07
    _dt
    -0.06
     нею
    -0.06
    QueryBuilder
    -0.06
    -boot
    -0.06
    _DRV
    -0.06
     heterosexual
    -0.06
    -dr
    -0.06
    /db
    -0.06
    สต
    -0.06
    POSITIVE LOGITS
     leveraging
    0.07
     ≠
    0.07
     impressive
    0.07
    Different
    0.07
     steroids
    0.06
    Bes
    0.06
     unparalleled
    0.06
     Ψ
    0.06
     informative
    0.06
     [{
    0.06
    Activations Density 0.006%

    No Known Activations