© 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. 93051
    Prev
    Next
    INDEX
    Explanations

    terms related to usage and applications of materials or 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
    arge
    -0.07
    AGO
    -0.07
    .loc
    -0.06
    razier
    -0.06
    úc
    -0.06
    uet
    -0.06
    ãĤ¥
    -0.06
    _Source
    -0.06
    letal
    -0.06
    ä½ı
    -0.06
    POSITIVE LOGITS
     in
    0.07
     sebagai
    0.07
     elsewhere
    0.07
    à¹ĥà¸Ļà¸ģาร
    0.06
    ADDE
    0.06
     for
    0.06
    íĨłíĨł
    0.06
    weise
    0.06
    bsp
    0.06
    para
    0.06
    Activations Density 0.019%

    No Known Activations