© 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 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. 84271
    Prev
    Next
    INDEX
    Explanations

    references to dietary ingredients and additives

    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
    raki
    -0.09
    alore
    -0.08
    ilib
    -0.07
     åł
    -0.07
    MeasureSpec
    -0.07
    gre
    -0.07
    .Toolkit
    -0.07
    ulumi
    -0.07
    -urlencoded
    -0.06
    oot
    -0.06
    POSITIVE LOGITS
     stabil
    0.06
     Milo
    0.06
     artificial
    0.06
     invert
    0.06
     pres
    0.06
     Brill
    0.06
    _CALLBACK
    0.06
     added
    0.06
    ï¼
    0.06
    ulse
    0.06
    Activations Density 0.002%

    No Known Activations