© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106432
    Prev
    Next
    INDEX
    Explanations

    instances of the word "until," indicating conditions or timelines in the context of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ýš
    -0.07
    ostel
    -0.07
    ãĤ¤ãĥĦ
    -0.07
    enco
    -0.06
    гÑĢад
    -0.06
    ê¸°ë¡ľ
    -0.06
    eliac
    -0.06
    _fh
    -0.06
    aser
    -0.06
    olicit
    -0.06
    POSITIVE LOGITS
    /if
    0.07
     unless
    0.07
    VERN
    0.06
     absolutely
    0.06
     we
    0.06
     either
    0.06
    berra
    0.06
     lac
    0.06
    /un
    0.06
    afa
    0.06
    Activations Density 0.011%

    No Known Activations