© 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. 17-LLAMASCOPE-RES-131K
    11. 86793
    Prev
    Next
    INDEX
    Explanations

    numerical values or references to steps in procedures

    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
    uko
    -0.07
    HeaderValue
    -0.07
    unta
    -0.07
    Ñĸка
    -0.06
     Www
    -0.06
    ÐĤ
    -0.06
    anz
    -0.06
    Æł
    -0.06
     Prov
    -0.06
    ookie
    -0.06
    POSITIVE LOGITS
     above
    0.07
     earlier
    0.06
    _fmt
    0.06
    Startup
    0.06
     ster
    0.06
    itm
    0.06
     Stoke
    0.06
    als
    0.06
    ateria
    0.06
    brids
    0.06
    Activations Density 0.018%

    No Known Activations