© 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. 72335
    Prev
    Next
    INDEX
    Explanations

    references to plot and analysis

    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
     TOO
    -0.10
     too
    -0.10
    Too
    -0.09
     Too
    -0.09
     ÑģлиÑĪком
    -0.08
    太
    -0.08
    -too
    -0.07
    ream
    -0.07
    too
    -0.07
    omm
    -0.07
    POSITIVE LOGITS
    ting
    0.09
    idian
    0.08
    ter
    0.08
    èİ
    0.07
    acco
    0.06
    ingu
    0.06
    zı
    0.06
    errupted
    0.06
    ritch
    0.06
     thick
    0.06
    Activations Density 0.008%

    No Known Activations