© 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. 108067
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific structures in sentences

    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
    rosso
    -0.07
    iros
    -0.07
    _LEG
    -0.06
    ynn
    -0.06
    arf
    -0.06
    rema
    -0.06
    hma
    -0.06
    enas
    -0.06
    agger
    -0.06
    coder
    -0.06
    POSITIVE LOGITS
     now
    0.13
     today
    0.11
    çİ°åľ¨
    0.11
    now
    0.11
     ahora
    0.11
    ä»Ĭå¹´
    0.10
    today
    0.10
     ä»Ĭ
    0.10
     Now
    0.09
    ä»ĬæĹ¥
    0.09
    Activations Density 0.019%

    No Known Activations