© 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. 55946
    Prev
    Next
    INDEX
    Explanations

    references to collaboration and teamwork in a professional context

    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
     forState
    -0.07
    aldi
    -0.07
    Sharper
    -0.07
    apia
    -0.07
    BuilderInterface
    -0.07
    cbc
    -0.07
     Claw
    -0.07
    kate
    -0.07
    olah
    -0.07
    æł·åŃIJ
    -0.07
    POSITIVE LOGITS
     unusually
    0.07
     unusual
    0.07
    fast
    0.07
    phere
    0.07
     unconventional
    0.06
     Resident
    0.06
     workaround
    0.06
     fast
    0.06
     required
    0.06
    ety
    0.06
    Activations Density 0.008%

    No Known Activations