© 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. 85707
    Prev
    Next
    INDEX
    Explanations

    )/

    np_max-act · gemini-2.0-flash

    complex mathematical expressions and relationships involving variables.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects numeric constants—especially floating‐point numbers—in mathematical expressions.

    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
     Sen
    -0.07
    拜
    -0.07
     PRI
    -0.06
     franchise
    -0.06
    -men
    -0.06
    Order
    -0.06
    _PENDING
    -0.06
     BUT
    -0.06
     autop
    -0.06
     revived
    -0.06
    POSITIVE LOGITS
    .fd
    0.07
     Tex
    0.07
     intermitt
    0.07
     cigaret
    0.07
     香港
    0.07
    оке
    0.06
     Tmin
    0.06
    _imag
    0.06
    蜘蛛词
    0.06
    金额
    0.06
    Activations Density 0.005%

    No Known Activations