© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 55749
    Prev
    Next
    INDEX
    Explanations

    descriptions of flavors and sensory qualities in beverages

    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
    å¡ļ
    -0.07
    ervice
    -0.07
    onz
    -0.06
    annes
    -0.06
     Record
    -0.06
    ìĸ¼
    -0.06
    íħľ
    -0.06
    uÃŃ
    -0.06
    ervices
    -0.06
     [[]
    -0.06
    POSITIVE LOGITS
    ìŀ¡
    0.07
     ìŀ¡
    0.06
     secondary
    0.06
     Secondary
    0.06
    -loss
    0.06
    gebung
    0.06
    ког
    0.06
    PEG
    0.05
     Coat
    0.05
    grese
    0.05
    Activations Density 0.006%

    No Known Activations