© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94381
    Prev
    Next
    INDEX
    Explanations

    terms related to business and operational processes

    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
     itself
    -0.08
     Levine
    -0.07
    omain
    -0.07
     Ãĥ
    -0.07
    nist
    -0.06
     druž
    -0.06
    riba
    -0.06
    -pills
    -0.06
    itti
    -0.06
    ýš
    -0.06
    POSITIVE LOGITS
     issues
    0.09
     considerations
    0.08
     concerns
    0.07
     requirements
    0.07
     constraints
    0.07
     mechanisms
    0.07
     issue
    0.07
    issues
    0.06
     aspects
    0.06
     Hatch
    0.06
    Activations Density 0.063%

    No Known Activations