© 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. 3122
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental and business contexts

    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
    ansen
    -0.08
    ometr
    -0.07
    ughs
    -0.07
    ivot
    -0.07
     lục
    -0.07
    osti
    -0.07
    ILA
    -0.07
    égor
    -0.07
    lich
    -0.06
    lsen
    -0.06
    POSITIVE LOGITS
     analogue
    0.07
    -changing
    0.07
    472
    0.07
    /context
    0.06
     Hill
    0.06
    azor
    0.06
    -wide
    0.06
    -shift
    0.06
    orama
    0.06
    ForResource
    0.06
    Activations Density 0.014%

    No Known Activations