© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125075
    Prev
    Next
    INDEX
    Explanations

    day

    np_max-act · gemini-2.0-flash

    This neuron activates on numerical measurements (especially decimal and other numeric values) in the methods or results sections.

    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
    _IF
    -0.06
    _PRE
    -0.06
    egen
    -0.06
     annon
    -0.06
    blogs
    -0.06
     Sandy
    -0.06
     Came
    -0.06
    Professor
    -0.06
    .ErrorMessage
    -0.06
    InputDialog
    -0.06
    POSITIVE LOGITS
     Gerry
    0.07
     구성
    0.07
     rents
    0.06
     {}\
    0.06
    нож
    0.06
     другие
    0.06
     stake
    0.06
     ####
    0.06
    ทางการ
    0.06
     mountains
    0.06
    Activations Density 0.010%

    No Known Activations