© 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. 72111
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods and events, particularly those related to the New Year

    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
    377
    -0.07
    zos
    -0.07
    IDGET
    -0.06
    amburger
    -0.06
    irs
    -0.06
    ets
    -0.06
    ụp
    -0.06
    .community
    -0.06
    ocker
    -0.06
    okers
    -0.06
    POSITIVE LOGITS
    atings
    0.07
    fresh
    0.07
    *******************************************************************************/↵
    0.06
     fresh
    0.06
    imitives
    0.06
    æĸ°çļĦ
    0.06
    宿
    0.06
    Dump
    0.06
    æ¡
    0.06
    .same
    0.06
    Activations Density 0.002%

    No Known Activations