© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 26679
    Prev
    Next
    INDEX
    Explanations

    specific dates and numerical information related to events or births

    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
     Sul
    -0.07
    FromArray
    -0.07
    fabs
    -0.07
    phylum
    -0.07
    ecs
    -0.07
     voleb
    -0.06
    eton
    -0.06
    urum
    -0.06
    NECT
    -0.06
    pons
    -0.06
    POSITIVE LOGITS
    orda
    0.07
     ç·
    0.06
    ignum
    0.06
    ibil
    0.05
     Giles
    0.05
     pÅĻiÄįemž
    0.05
    ãĥ©ãĤ¤ãĥ³
    0.05
    std
    0.05
     FY
    0.05
    iembre
    0.05
    Activations Density 0.005%

    No Known Activations