© 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. 106529
    Prev
    Next
    INDEX
    Explanations

    snippets of code associated with function definitions and calculations

    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
    683
    -0.06
    ød
    -0.06
     strtok
    -0.06
     scenario
    -0.06
     continuous
    -0.06
    Segue
    -0.06
     gob
    -0.06
     Matthias
    -0.06
    uge
    -0.06
    ekt
    -0.06
    POSITIVE LOGITS
     Hamp
    0.07
    usch
    0.07
     Slee
    0.06
    ONUS
    0.06
     dep
    0.06
     SQUARE
    0.06
    Surname
    0.06
    _spin
    0.06
    ij¸
    0.06
    zell
    0.06
    Activations Density 0.012%

    No Known Activations