© 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. 42151
    Prev
    Next
    INDEX
    Explanations

    references to alternative protein sources and food innovations

    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
     æ©
    -0.06
     cum
    -0.06
     genie
    -0.06
    idend
    -0.06
    illard
    -0.06
     fost
    -0.06
    ãģĸ
    -0.06
    cum
    -0.06
     block
    -0.06
    atal
    -0.06
    POSITIVE LOGITS
     Insecta
    0.08
    곤
    0.07
     cricket
    0.07
     feeds
    0.07
     protein
    0.07
    íĩ´
    0.07
    -hooks
    0.07
     Hancock
    0.07
    616
    0.07
    ipes
    0.07
    Activations Density 0.003%

    No Known Activations