© 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. 94199
    Prev
    Next
    INDEX
    Explanations

    references to time, specifically relating to hours and schedules

    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
    aras
    -0.07
    ãĤ¯ãĥŃ
    -0.07
    oÄŁ
    -0.07
    ocale
    -0.06
    ãĥĮ
    -0.06
    lub
    -0.06
    ģm
    -0.06
    ánÃŃ
    -0.06
    ither
    -0.06
    Ã¤ÃŁ
    -0.06
    POSITIVE LOGITS
     comeback
    0.08
     Cunningham
    0.07
    ccoli
    0.07
     resumed
    0.07
    again
    0.06
    _resume
    0.06
    pled
    0.06
     later
    0.06
     again
    0.06
    Æ°
    0.06
    Activations Density 0.013%

    No Known Activations