© 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. 69553
    Prev
    Next
    INDEX
    Explanations

    numerical values related to measurements and quantities

    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
    amber
    -0.06
    ippet
    -0.06
     Mans
    -0.06
    ongo
    -0.06
    fell
    -0.06
    ixon
    -0.06
    cope
    -0.06
    itler
    -0.06
     Diet
    -0.06
    amic
    -0.06
    POSITIVE LOGITS
     depending
    0.20
    depending
    0.17
     Depending
    0.12
    Depending
    0.11
     depend
    0.11
     depends
    0.10
     dependent
    0.10
    depends
    0.10
     Depends
    0.10
     depended
    0.10
    Activations Density 0.017%

    No Known Activations