© 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. 84371
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment or appreciation

    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
     Verse
    -0.07
    à¤ķरण
    -0.07
    /from
    -0.07
    eatures
    -0.07
    out
    -0.07
    caler
    -0.06
    resh
    -0.06
    eature
    -0.06
    bear
    -0.06
    269
    -0.06
    POSITIVE LOGITS
    ably
    0.09
     opportunities
    0.07
     opportunity
    0.07
    onse
    0.07
     rub
    0.07
     Kling
    0.07
    idenav
    0.07
    ingly
    0.07
    ful
    0.07
     Pul
    0.07
    Activations Density 0.007%

    No Known Activations