© 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 EvalsExportsinterp-engineNEWAPI 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. 2347
    Prev
    Next
    INDEX
    Explanations

    terms related to organic compounds and their derivatives

    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
    392
    -0.08
    an
    -0.08
    arrow
    -0.07
    ofi
    -0.07
    obra
    -0.07
    anje
    -0.07
    oblin
    -0.07
    odash
    -0.07
    uman
    -0.06
    iva
    -0.06
    POSITIVE LOGITS
    ated
    0.10
    ating
    0.07
    ized
    0.07
    serter
    0.07
    transfer
    0.07
     enc
    0.06
     rollback
    0.06
    ATED
    0.06
    ène
    0.06
    館
    0.06
    Activations Density 0.014%

    No Known Activations