© 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. 87380
    Prev
    Next
    INDEX
    Explanations

    technical terms related to blending and mixing processes

    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
     cooker
    -0.08
    ustum
    -0.08
     cháy
    -0.08
    nock
    -0.07
    úi
    -0.07
    ManagerInterface
    -0.07
    æĤī
    -0.07
    etable
    -0.07
    ordion
    -0.07
    EMU
    -0.07
    POSITIVE LOGITS
     Cann
    0.07
     dough
    0.06
     Dough
    0.06
     cann
    0.06
    xFFF
    0.06
     mode
    0.06
     Cannes
    0.05
     Ba
    0.05
     Set
    0.05
     Scala
    0.05
    Activations Density 0.008%

    No Known Activations