© 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. 15-LLAMASCOPE-RES-131K
    11. 89838
    Prev
    Next
    INDEX
    Explanations

    concepts related to biological classification and taxonomy

    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
    ³
    -0.07
    cao
    -0.07
    еÑĤелÑĮ
    -0.06
     anonym
    -0.06
    EditMode
    -0.06
    edla
    -0.06
    ocale
    -0.06
    ROC
    -0.06
    ingular
    -0.06
    _DI
    -0.06
    POSITIVE LOGITS
     convention
    0.09
     definition
    0.08
     slightly
    0.07
     Decision
    0.07
     Definition
    0.07
     definitions
    0.07
     view
    0.07
    definitions
    0.07
     defs
    0.07
    -definition
    0.07
    Activations Density 0.054%

    No Known Activations