© 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. 119746
    Prev
    Next
    INDEX
    Explanations

    technical and mathematical terminology, specifically related to equations and scientific representations

    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
     Westbrook
    -0.06
    ASM
    -0.06
    ASI
    -0.06
    ä¹Ļ
    -0.06
    odal
    -0.06
    enschaft
    -0.06
    tright
    -0.06
    _URI
    -0.06
     electroly
    -0.06
    eps
    -0.05
    POSITIVE LOGITS
    коп
    0.07
     {?>↵
    0.07
     Smoke
    0.07
    θη
    0.07
     PCB
    0.07
     Coal
    0.07
     Flame
    0.06
     pitch
    0.06
    алом
    0.06
    ãĥ¡ãĥ©
    0.06
    Activations Density 0.024%

    No Known Activations