© 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. 73570
    Prev
    Next
    INDEX
    Explanations

    sports events

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens containing a decimal point, effectively detecting floating-point numbers in the text.

    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
    (lp
    -0.07
    gest
    -0.07
    (join
    -0.07
     libc
    -0.06
    .parser
    -0.06
    INI
    -0.06
    .AF
    -0.06
    _UNICODE
    -0.06
    Income
    -0.06
    意义
    -0.06
    POSITIVE LOGITS
     Conc
    0.07
    uche
    0.06
    .decorators
    0.06
     ком
    0.06
    γα
    0.06
     اض
    0.06
     Humb
    0.06
     eliminar
    0.06
    骑
    0.06
    .removeClass
    0.06
    Activations Density 0.026%

    No Known Activations