© 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. 94566
    Prev
    Next
    INDEX
    Explanations

    adjectives describing intelligence and uniqueness in pets

    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
     cater
    -0.07
     Gerr
    -0.07
    gov
    -0.06
     riff
    -0.06
     Elder
    -0.06
    ForResult
    -0.06
     Cater
    -0.06
    248
    -0.06
     Brewer
    -0.06
    elves
    -0.06
    POSITIVE LOGITS
    ewith
    0.07
    paque
    0.07
    pline
    0.07
    лиÑĪком
    0.07
    izzo
    0.07
     irrig
    0.07
    inand
    0.07
    ertype
    0.07
    iline
    0.07
     inheritance
    0.06
    Activations Density 0.001%

    No Known Activations