© 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. 60723
    Prev
    Next
    INDEX
    Explanations

    phrases indicating scheduling or frequency of 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
    ugg
    -0.08
     simultaneously
    -0.07
     continuously
    -0.07
    oppel
    -0.06
     VÅ¡ech
    -0.06
    ìĸ
    -0.06
    enta
    -0.06
     prematurely
    -0.06
    ishi
    -0.06
    iani
    -0.06
    POSITIVE LOGITS
     occasional
    0.15
     spor
    0.11
     whenever
    0.10
     occasionally
    0.10
     occas
    0.10
     only
    0.09
     Spor
    0.09
    only
    0.09
     Occasionally
    0.09
     ocas
    0.09
    Activations Density 0.025%

    No Known Activations