© 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. 60491
    Prev
    Next
    INDEX
    Explanations

    elements related to dietary guidelines and health classifications

    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
     ze
    -0.06
    عات
    -0.06
    _ABI
    -0.06
    unik
    -0.06
     Friedman
    -0.06
    orz
    -0.06
    ABL
    -0.06
    ULA
    -0.06
    enga
    -0.06
    .lp
    -0.06
    POSITIVE LOGITS
     Panel
    0.08
     inputs
    0.08
     scientific
    0.07
     reviewers
    0.07
     BASIS
    0.07
     eval
    0.06
     Gul
    0.06
     Heard
    0.06
     Fam
    0.06
    Expert
    0.06
    Activations Density 0.049%

    No Known Activations