© 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. 123938
    Prev
    Next
    INDEX
    Explanations

    terms related to academic or literary analysis

    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
    avel
    -0.06
    amm
    -0.06
     Mits
    -0.06
    æĸ¹
    -0.06
    å¤ĩ
    -0.06
    EMPL
    -0.06
    ypsy
    -0.06
    idi
    -0.06
    cam
    -0.05
    Pocket
    -0.05
    POSITIVE LOGITS
     anywhere
    0.08
     ever
    0.08
     anything
    0.08
     varsa
    0.07
    anything
    0.07
    Anywhere
    0.07
    à¹ĥà¸Ķ
    0.07
     Anything
    0.07
    íļĮ
    0.07
    æľīä»Ģä¹Ī
    0.07
    Activations Density 0.026%

    No Known Activations