© 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. 9-LLAMASCOPE-RES-131K
    11. 94794
    Prev
    Next
    INDEX
    Explanations

    key nouns and notable concepts in various contexts

    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
    nesc
    -0.07
    uitka
    -0.07
    LinkId
    -0.06
    ugas
    -0.06
    Defs
    -0.06
    avou
    -0.06
    ICAST
    -0.06
    ÌĨ
    -0.06
    gratis
    -0.06
    ï¼¥
    -0.06
    POSITIVE LOGITS
    an
    0.08
    ons
    0.06
    ooks
    0.06
    innacle
    0.06
    anton
    0.06
    icz
    0.06
     incremental
    0.06
    obar
    0.06
    anny
    0.06
    aton
    0.06
    Activations Density 0.013%

    No Known Activations