© 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. 15-LLAMASCOPE-RES-131K
    11. 86902
    Prev
    Next
    INDEX
    Explanations

    concepts related to knowledge and understanding of humanity

    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
    ourcem
    -0.07
    ãĥ¼ãĤ¿ãĥ¼
    -0.07
    dal
    -0.07
    rente
    -0.07
    ison
    -0.06
    uese
    -0.06
    аниÑİ
    -0.06
    erville
    -0.06
     ign
    -0.06
     recogn
    -0.06
    POSITIVE LOGITS
     merely
    0.09
     simply
    0.07
    nor
    0.07
     nor
    0.07
    ensch
    0.07
    nem
    0.06
     Simply
    0.06
    Simply
    0.06
    ahir
    0.06
    æ¥ŃåĭĻ
    0.06
    Activations Density 0.020%

    No Known Activations