© 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. 29780
    Prev
    Next
    INDEX
    Explanations

    terms related to nutrition and nutrients

    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
    hood
    -0.08
    ness
    -0.08
    curr
    -0.07
    go
    -0.07
    azine
    -0.06
    orca
    -0.06
    hook
    -0.06
    ork
    -0.06
    yer
    -0.06
    down
    -0.06
    POSITIVE LOGITS
    -rich
    0.09
     Airways
    0.07
    parer
    0.07
     пиÑĤаниÑı
    0.07
    ickets
    0.07
     Král
    0.07
    Wars
    0.07
    emple
    0.07
    -packed
    0.07
    _Bool
    0.06
    Activations Density 0.005%

    No Known Activations