© 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. 71039
    Prev
    Next
    INDEX
    Explanations

    terms related to time and measurement in the context of service and work

    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
    ooter
    -0.06
    ideshow
    -0.06
     tomorrow
    -0.06
     hourly
    -0.06
    arf
    -0.06
    .interval
    -0.06
    大人
    -0.06
    ivas
    -0.06
    emaker
    -0.06
    eful
    -0.06
    POSITIVE LOGITS
    umin
    0.08
     devoted
    0.07
     spent
    0.07
    bie
    0.07
     per
    0.07
     navÃŃc
    0.07
     commitment
    0.06
    ca
    0.06
     committed
    0.06
     requirement
    0.06
    Activations Density 0.014%

    No Known Activations