© 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. 84224
    Prev
    Next
    INDEX
    Explanations

    mathematical notations related to dimensions and functions

    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
    ality
    -0.07
    wiki
    -0.07
    undle
    -0.07
    Äįku
    -0.06
    ÙĩاÛĮÛĮ
    -0.06
    lili
    -0.06
    vro
    -0.06
    s
    -0.06
    olu
    -0.06
    è¡
    -0.06
    POSITIVE LOGITS
    ousse
    0.07
    ":""
    0.07
    lements
    0.06
    UTE
    0.06
    243
    0.06
    /helper
    0.06
    oster
    0.06
    embr
    0.06
    up
    0.06
    623
    0.06
    Activations Density 0.060%

    No Known Activations