© 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. 97381
    Prev
    Next
    INDEX
    Explanations

    technical terminology and concepts related to network modeling and performance analysis

    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
     sek
    -0.06
    teen
    -0.06
    ys
    -0.06
    enburg
    -0.06
     secondary
    -0.06
    enger
    -0.05
    aign
    -0.05
    hang
    -0.05
     Secondary
    -0.05
    ors
    -0.05
    POSITIVE LOGITS
    emain
    0.07
    ãģıãĤĮãģŁ
    0.07
    è£ķ
    0.07
    /MIT
    0.07
    utzer
    0.07
    ż
    0.07
    apis
    0.07
    unist
    0.07
    Intialized
    0.07
    alley
    0.07
    Activations Density 0.034%

    No Known Activations