© 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. 105008
    Prev
    Next
    INDEX
    Explanations

    details about medical treatments and their effects

    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
    _unix
    -0.07
    unities
    -0.07
    ze
    -0.06
    indow
    -0.06
     neither
    -0.06
    oor
    -0.06
     Benedict
    -0.06
    /font
    -0.05
    legal
    -0.05
    ÙĴت
    -0.05
    POSITIVE LOGITS
     high
    0.13
     low
    0.11
     large
    0.11
    é«ĺ
    0.10
    high
    0.10
     big
    0.10
    -high
    0.09
    large
    0.09
    _large
    0.09
    .high
    0.09
    Activations Density 0.103%

    No Known Activations