© 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. 59076
    Prev
    Next
    INDEX
    Explanations

    concepts related to structure, characteristics, and qualitative aspects of entities or scenarios

    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
    лÑıн
    -0.08
    inder
    -0.08
    alian
    -0.08
    adian
    -0.07
    æĹıèĩªæ²»
    -0.07
    createView
    -0.07
    emaker
    -0.07
    ARIANT
    -0.07
    ube
    -0.07
    placeholders
    -0.07
    POSITIVE LOGITS
     terms
    0.07
     size
    0.06
    -wise
    0.06
    247
    0.06
     appearance
    0.06
     wise
    0.06
    ys
    0.06
     critic
    0.06
     sake
    0.06
    agua
    0.06
    Activations Density 0.030%

    No Known Activations