© 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. 55210
    Prev
    Next
    INDEX
    Explanations

    concepts related to energy balance and survival adaptations in living organisms

    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
    afen
    -0.07
    phylum
    -0.07
    ierge
    -0.07
    retch
    -0.07
    ypad
    -0.07
    @mail
    -0.07
    enet
    -0.07
    /Foundation
    -0.07
    istol
    -0.07
    idot
    -0.07
    POSITIVE LOGITS
     fitness
    0.07
     investment
    0.07
     optim
    0.07
     Fitness
    0.07
     maxim
    0.07
     Belly
    0.06
     resource
    0.06
     altru
    0.06
     Resource
    0.06
     provisioning
    0.06
    Activations Density 0.004%

    No Known Activations