© 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. 15-LLAMASCOPE-RES-131K
    11. 89885
    Prev
    Next
    INDEX
    Explanations

    concepts related to enzymes and their roles in biochemical processes

    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
    azor
    -0.08
    å¹ķ
    -0.08
     Pond
    -0.07
    ço
    -0.07
    .inject
    -0.07
    éné
    -0.07
    ÑĥÑĩ
    -0.07
    sik
    -0.07
     cref
    -0.07
    पत
    -0.06
    POSITIVE LOGITS
     priv
    0.07
     activity
    0.06
    /editor
    0.06
    erase
    0.06
     blade
    0.06
     function
    0.06
     moon
    0.06
     Belt
    0.06
     Moon
    0.06
     knife
    0.06
    Activations Density 0.082%

    No Known Activations