© 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. 31093
    Prev
    Next
    INDEX
    Explanations

    perf

    np_max-act · gemini-2.0-flash

    terms related to performance monitoring and profiling in computing.

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

    This neuron activates on occurrences of the string “perf” (and its extensions like perf-inject, perf_event, etc.) 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
    üncü
    -0.07
    (VALUE
    -0.07
     woll
    -0.07
    ırlar
    -0.07
     mascara
    -0.06
    subplot
    -0.06
    ;;;;;;;;
    -0.06
     požadav
    -0.06
    glomer
    -0.06
    utowired
    -0.06
    POSITIVE LOGITS
     secret
    0.07
     Wy
    0.07
     outsiders
    0.07
     collections
    0.07
    _il
    0.07
     ap
    0.06
     strengthen
    0.06
     constit
    0.06
     promotion
    0.06
     carc
    0.06
    Activations Density 0.017%

    No Known Activations