© 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. 5319
    Prev
    Next
    INDEX
    Explanations

    keywords related to software and system specifications

    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
    peria
    -0.08
    ãĥ³ãĥIJ
    -0.07
    iphone
    -0.07
    _ANDROID
    -0.07
    -ios
    -0.06
    GenerationStrategy
    -0.06
    ellular
    -0.06
     cellForRowAtIndexPath
    -0.06
    ÙĪÙĨا
    -0.06
     Tobias
    -0.06
    POSITIVE LOGITS
    /boot
    0.09
     Windows
    0.08
     Window
    0.08
    Windows
    0.07
     Win
    0.07
    boot
    0.07
     boot
    0.07
     Microsoft
    0.07
    Win
    0.07
     windows
    0.07
    Activations Density 0.038%

    No Known Activations