Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78498
    Prev
    Next
    INDEX
    Explanations

    references to gender and societal roles

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

    Significant nouns that appear near paragraph transitions or complete key thoughts, often representing concrete entities, locations, or concepts central to the text's meaning.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ếp
    -0.07
    noinspection
    -0.07
    .dsl
    -0.06
    rade
    -0.06
    azole
    -0.06
    è£ľ
    -0.06
    hoe
    -0.06
    eder
    -0.06
    idi
    -0.06
    ount
    -0.06
    POSITIVE LOGITS
     respectively
    0.08
    okino
    0.07
    aska
    0.07
    ëĵ¯
    0.07
     alike
    0.06
     Uncategorized
    0.06
    qli
    0.06
    aset
    0.06
    achel
    0.06
    omik
    0.06
    Activations Density 0.171%

    No Known Activations