© 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. 89395
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps related to articles or updates

    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
    agli
    -0.07
    ahi
    -0.07
    olan
    -0.07
    ãĥ«ãĤ¯
    -0.07
    ÏģοÏħ
    -0.06
     ìµľê·¼
    -0.06
    obo
    -0.06
    uje
    -0.06
     Burl
    -0.06
     recently
    -0.06
    POSITIVE LOGITS
    Originally
    0.07
    åīĩ
    0.06
    ear
    0.06
     orig
    0.06
    eca
    0.06
     im
    0.06
     originally
    0.06
    apas
    0.06
     original
    0.06
    Ø°ÙĬ
    0.06
    Activations Density 0.003%

    No Known Activations