© 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. 31336
    Prev
    Next
    INDEX
    Explanations

    chemical properties and behaviors of substances

    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
    tgl
    -0.07
    à¸Ńà¸Ļ
    -0.07
    woke
    -0.07
    á»Ĩ
    -0.06
    ekim
    -0.06
    sian
    -0.06
    нож
    -0.06
    ffen
    -0.06
    ège
    -0.06
    åŀ
    -0.06
    POSITIVE LOGITS
    oria
    0.07
    vat
    0.07
    åį±
    0.07
    æ½®
    0.06
    boxed
    0.06
    aland
    0.06
     Sunder
    0.06
     orth
    0.06
     prolonged
    0.06
    çŃĴ
    0.06
    Activations Density 0.003%

    No Known Activations