© 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. 126306
    Prev
    Next
    INDEX
    Explanations

    references to time, including moments, durations, and decision points

    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
     zatÃŃm
    -0.08
    gnore
    -0.07
    ovÃŃ
    -0.07
    fak
    -0.07
     continued
    -0.07
    motion
    -0.06
     slowly
    -0.06
     ìķĦì§ģ
    -0.06
    elia
    -0.06
    _INCLUDED
    -0.06
    POSITIVE LOGITS
     briefly
    0.09
     even
    0.09
     sogar
    0.08
     temporarily
    0.08
    even
    0.08
     temporary
    0.07
     Temporary
    0.07
    çĶļèĩ³
    0.07
    brief
    0.07
    ä¸Ģ度
    0.07
    Activations Density 0.014%

    No Known Activations