© 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. 118744
    Prev
    Next
    INDEX
    Explanations

    key biological processes and proteins involved in cellular functions

    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
    Alive
    -0.07
    аÑĢаÑĤ
    -0.07
    .selectAll
    -0.07
    ROSS
    -0.07
    uilder
    -0.06
    ìĹ¼
    -0.06
    ÑĢаÑħ
    -0.06
    artz
    -0.06
    deen
    -0.06
     geil
    -0.06
    POSITIVE LOGITS
     recruited
    0.07
     assembly
    0.07
     formed
    0.07
     forming
    0.07
     contacts
    0.07
     association
    0.07
     assembling
    0.07
     associations
    0.06
     assembled
    0.06
     Contacts
    0.06
    Activations Density 0.013%

    No Known Activations