© 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. 62642
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of time intervals

    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
     ust
    -0.07
    ampie
    -0.07
    ارÙĩ
    -0.06
    оÑģÑĮ
    -0.06
     finally
    -0.06
     ba
    -0.06
    aits
    -0.06
    à¹ĩà¸Ī
    -0.06
    burger
    -0.06
     Except
    -0.06
    POSITIVE LOGITS
     passing
    0.08
     decade
    0.07
    ëĵ
    0.07
    è¶Ĭ
    0.07
     annum
    0.07
     time
    0.07
    hel
    0.06
    CJK
    0.06
     Passing
    0.06
     Continued
    0.06
    Activations Density 0.007%

    No Known Activations