© 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. 938
    Prev
    Next
    INDEX
    Explanations

    challenges, obstacles, difficulties

    np_max-act · gemini-2.0-flash

    This neuron lights up on subword tokens representing decimal/fractional numeric values (e.g. the pieces of “3.5 onzas”).

    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
     sokak
    -0.07
     Laur
    -0.07
     فارس
    -0.06
    มาก
    -0.06
    agraph
    -0.06
    icated
    -0.06
     περιοχή
    -0.06
     diagram
    -0.06
     morphology
    -0.06
    ショ
    -0.06
    POSITIVE LOGITS
    $post
    0.07
     galaxy
    0.06
     qw
    0.06
    kim
    0.06
    ROM
    0.06
    =>"
    0.06
     stanov
    0.06
     Pollution
    0.06
    [a
    0.06
    .Room
    0.06
    Activations Density 0.573%

    No Known Activations