© 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. 9055
    Prev
    Next
    INDEX
    Explanations

    unit conversions

    np_max-act · gemini-2.0-flash

    numerical values and their conversions across different measurement units.

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

    This neuron responds to numeric tokens (including multi‐digit numbers and decimal fragments) in measurement‐and‐conversion contexts.

    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
    Hy
    -0.07
    ycle
    -0.07
    _corners
    -0.07
    cession
    -0.06
     효과
    -0.06
    coh
    -0.06
     Asphalt
    -0.06
     interpretation
    -0.06
    -labelledby
    -0.06
     Calculation
    -0.06
    POSITIVE LOGITS
    >{{$
    0.07
     enduring
    0.07
     Photograph
    0.06
     ген
    0.06
     تلك
    0.06
     Caption
    0.06
    歷
    0.06
     xmm
    0.06
     inaugural
    0.06
     finalists
    0.06
    Activations Density 0.041%

    No Known Activations