© 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. 120680
    Prev
    Next
    INDEX
    Explanations

    the word "den" 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
    rtl
    -0.07
     Wise
    -0.07
    anvas
    -0.06
    ello
    -0.06
     Jefferson
    -0.06
    RTL
    -0.05
     Fee
    -0.05
     soll
    -0.05
     Wo
    -0.05
     Trace
    -0.05
    POSITIVE LOGITS
    ">//
    0.07
    lian
    0.07
    Ãĭ
    0.06
    ITCH
    0.06
    iaux
    0.06
    isnan
    0.06
    :convert
    0.06
    Boot
    0.06
    758
    0.06
    643
    0.06
    Activations Density 0.000%

    No Known Activations