© 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. 86365
    Prev
    Next
    INDEX
    Explanations

    references to comparisons and contrasts

    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
    .scalablytyped
    -0.08
    eydi
    -0.07
    ')==
    -0.07
    azer
    -0.07
    Inlining
    -0.07
    znám
    -0.07
    AGMA
    -0.07
    oltip
    -0.07
     EXEMPLARY
    -0.07
    ruz
    -0.07
    POSITIVE LOGITS
     difference
    0.15
     Difference
    0.12
     differences
    0.12
    difference
    0.12
    Difference
    0.11
     Differences
    0.10
     comparison
    0.10
    both
    0.10
     whereas
    0.10
     both
    0.10
    Activations Density 0.065%

    No Known Activations