© 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. 73975
    Prev
    Next
    INDEX
    Explanations

    complex sentence structures and punctuation

    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
    isel
    -0.07
    rena
    -0.07
    uran
    -0.06
     trib
    -0.06
    iren
    -0.06
    bjerg
    -0.06
     fore
    -0.05
    Muon
    -0.05
     indebted
    -0.05
     Brun
    -0.05
    POSITIVE LOGITS
     Uncategorized
    0.07
    SharedPtr
    0.07
     senses
    0.07
    ForResult
    0.07
    ModelProperty
    0.07
    utter
    0.06
     Farrell
    0.06
     doz
    0.06
    -slot
    0.06
    ampp
    0.06
    Activations Density 0.001%

    No Known Activations