© 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. 62815
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries related to understanding or exploring concepts

    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
    ãģ¾ãģļ
    -0.09
    zÃŃ
    -0.08
    наÑĩала
    -0.07
     és
    -0.07
    ÑĪкÑĥ
    -0.07
    âķĹ
    -0.07
     vÃł
    -0.06
    ÂĿ
    -0.06
    åĴĮ
    -0.06
    -Based
    -0.06
    POSITIVE LOGITS
     it
    0.11
     thereof
    0.10
     its
    0.09
    å®ĥ们
    0.09
     therein
    0.09
     ê·¸ê²ĥ
    0.09
     therefore
    0.09
     thereby
    0.08
     consequently
    0.08
     possibly
    0.07
    Activations Density 0.033%

    No Known Activations