© 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. 89208
    Prev
    Next
    INDEX
    Explanations

    components related to genetic regulation and protein interactions

    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
    amar
    -0.06
    weathermap
    -0.06
     trait
    -0.06
     repost
    -0.06
    spo
    -0.06
    eker
    -0.06
    tility
    -0.06
    apixel
    -0.06
    enties
    -0.06
     paramString
    -0.06
    POSITIVE LOGITS
     transcription
    0.10
     nuclear
    0.08
     Nuclear
    0.08
     promoter
    0.07
    Drv
    0.07
     regulatory
    0.07
    quirrel
    0.07
     enh
    0.06
    oshi
    0.06
    ULLET
    0.06
    Activations Density 0.111%

    No Known Activations