© 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. 123741
    Prev
    Next
    INDEX
    Explanations

    programming keywords and commands

    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
     æ¼
    -0.07
    edar
    -0.07
    UTILITY
    -0.07
    eki
    -0.07
    CLR
    -0.07
    ÏĢει
    -0.07
    antz
    -0.06
    kuk
    -0.06
     Rosenstein
    -0.06
    .Experimental
    -0.06
    POSITIVE LOGITS
     tre
    0.07
    aged
    0.06
    avern
    0.06
    uos
    0.06
    -manager
    0.06
    UGE
    0.06
    uge
    0.06
    UES
    0.06
     jadx
    0.06
    U
    0.06
    Activations Density 0.000%

    No Known Activations