© 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. 92758
    Prev
    Next
    INDEX
    Explanations

    quantifiable aspects of dietary and nutritional information

    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
     antibiot
    -0.07
    žÃŃ
    -0.07
    undy
    -0.07
    ilty
    -0.06
    imuth
    -0.06
    antha
    -0.06
    ermen
    -0.06
    estre
    -0.06
     cytok
    -0.06
    ewis
    -0.06
    POSITIVE LOGITS
     ket
    0.08
     ketogenic
    0.08
     Atkins
    0.07
     Ket
    0.07
     Fischer
    0.07
     keto
    0.07
    pane
    0.07
    ê·ľ
    0.06
     Stub
    0.06
    ket
    0.06
    Activations Density 0.001%

    No Known Activations