© 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. 117580
    Prev
    Next
    INDEX
    Explanations

    references to time, place, and their significance in a narrative

    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
    .opt
    -0.07
    egl
    -0.07
    essim
    -0.07
    ÛĮدÙĩ
    -0.06
    Æ°a
    -0.06
    èn
    -0.06
     older
    -0.06
    hurst
    -0.06
    faf
    -0.06
    æĻĤ代
    -0.06
    POSITIVE LOGITS
     eventual
    0.11
     later
    0.11
    later
    0.10
     ultimately
    0.09
     eventually
    0.09
     später
    0.08
    Later
    0.08
    æľĢçµĤ
    0.08
     Later
    0.08
     tomorrow
    0.07
    Activations Density 0.025%

    No Known Activations