© 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 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. 131051
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate careful observation or scrutiny

    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
    ген
    -0.07
    uchen
    -0.07
    andler
    -0.07
    æĪª
    -0.07
    окон
    -0.06
    adio
    -0.06
    iev
    -0.06
    лÑĥÑĩ
    -0.06
    dez
    -0.06
    chio
    -0.06
    POSITIVE LOGITS
     detail
    0.09
     details
    0.09
    detail
    0.08
    ç»Ĩ
    0.08
    ingly
    0.07
    .detail
    0.07
     Detail
    0.07
    ürk
    0.06
    -detail
    0.06
    igans
    0.06
    Activations Density 0.012%

    No Known Activations