© 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. 87833
    Prev
    Next
    INDEX
    Explanations

    terms related to glycosyltransferase activities

    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
    act
    -0.07
    uess
    -0.06
    eah
    -0.06
    tÃŃ
    -0.06
    ryo
    -0.06
    üss
    -0.05
    uyen
    -0.05
    undler
    -0.05
    rib
    -0.05
    akh
    -0.05
    POSITIVE LOGITS
     longer
    0.07
     detox
    0.07
    DCF
    0.07
     amen
    0.07
     rel
    0.07
    ochen
    0.07
     length
    0.07
    μμ
    0.07
    è¶Ĭ
    0.07
    quet
    0.07
    Activations Density 0.000%

    No Known Activations