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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27631
    Prev
    Next
    INDEX
    Explanations

    terms related to food processing and preservation methods

    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
    icot
    -0.07
    rogram
    -0.06
    elligent
    -0.06
     lub
    -0.06
     feeds
    -0.06
    ingo
    -0.06
     feeding
    -0.06
    ë§ī
    -0.06
    imes
    -0.06
    -feed
    -0.06
    POSITIVE LOGITS
     preserve
    0.09
     preservation
    0.09
    loss
    0.08
     loss
    0.08
     retained
    0.08
     destruction
    0.08
     losses
    0.08
     irreversible
    0.08
    preserve
    0.07
     retains
    0.07
    Activations Density 0.048%

    No Known Activations