© 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. 72465
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance or significance of a concept or idea

    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
    ohan
    -0.07
    \Php
    -0.07
     Holland
    -0.06
    URA
    -0.06
    еÑģÑĤÑĮ
    -0.06
    lack
    -0.06
    atform
    -0.06
    outer
    -0.06
    olland
    -0.06
     holland
    -0.06
    POSITIVE LOGITS
    estre
    0.08
    586
    0.07
    isos
    0.07
     cf
    0.06
    eriod
    0.06
    ÙĮ
    0.06
    ToFit
    0.06
    åĿ¡
    0.06
    .mutable
    0.06
    lass
    0.06
    Activations Density 0.010%

    No Known Activations