© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 125066
    Prev
    Next
    INDEX
    Explanations

    expressions of artistic performance and critical commentary

    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
     Starter
    -0.08
    asin
    -0.07
    andest
    -0.07
    encers
    -0.07
    legend
    -0.06
    (ph
    -0.06
    gesch
    -0.06
    ampp
    -0.06
    uler
    -0.06
    usch
    -0.06
    POSITIVE LOGITS
     occasional
    0.07
    æµħ
    0.06
     ve
    0.06
    oret
    0.06
    benh
    0.06
    779
    0.06
     realistic
    0.06
    <HashMap
    0.06
    Ø´ÙĨ
    0.06
     Yankee
    0.06
    Activations Density 0.007%

    No Known Activations