© 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. 93342
    Prev
    Next
    INDEX
    Explanations

    references to recent updates or the latest information

    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
    ium
    -0.07
    éļĬ
    -0.07
    arians
    -0.07
    eed
    -0.07
    ÙĪÙĦÙĬ
    -0.07
     ovar
    -0.06
    aro
    -0.06
    æĴ
    -0.06
    eries
    -0.06
    âĨ
    -0.06
    POSITIVE LOGITS
    /latest
    0.10
     latest
    0.09
    latest
    0.09
     version
    0.09
    version
    0.07
     trend
    0.07
     episode
    0.07
     trends
    0.07
    dle
    0.07
    ssue
    0.06
    Activations Density 0.007%

    No Known Activations