© 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. 75336
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "demonstrate" and related terms

    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
    omo
    -0.09
    eler
    -0.08
    itet
    -0.07
    alah
    -0.07
    iff
    -0.07
    ern
    -0.07
     Sher
    -0.07
    ابت
    -0.07
    ãģª
    -0.07
    ponsive
    -0.07
    POSITIVE LOGITS
    stration
    0.15
    strate
    0.12
    /demo
    0.10
    ikan
    0.08
    ait
    0.07
    strar
    0.07
     tidal
    0.06
    446
    0.06
    ATRIX
    0.06
    TRA
    0.06
    Activations Density 0.018%

    No Known Activations