© 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. 98795
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the start or beginning of events

    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
    ewire
    -0.07
    ÐľÐŀ
    -0.06
    ائر
    -0.06
    ignite
    -0.06
    ilib
    -0.06
    _CSR
    -0.06
    /lab
    -0.06
    xBA
    -0.06
    dere
    -0.06
    ì¦Ī
    -0.06
    POSITIVE LOGITS
    841
    0.07
    uppe
    0.06
    st
    0.06
    úsqueda
    0.06
    adin
    0.06
    sole
    0.06
    pheric
    0.06
    vier
    0.06
    ackers
    0.06
    Å¡ÃŃ
    0.06
    Activations Density 0.009%

    No Known Activations