© 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. 73313
    Prev
    Next
    INDEX
    Explanations

    references to significant events or entities that may lead to future developments or changes

    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
     earlier
    -0.07
    caps
    -0.07
     throughout
    -0.06
    713
    -0.06
     finally
    -0.06
    soever
    -0.06
     alike
    -0.06
     grav
    -0.06
     first
    -0.06
     final
    -0.06
    POSITIVE LOGITS
    ,next
    0.10
    -next
    0.10
    (next
    0.09
     NEXT
    0.09
     Next
    0.09
     batch
    0.08
    next
    0.08
    NEXT
    0.08
    Next
    0.08
     iteration
    0.08
    Activations Density 0.044%

    No Known Activations