© 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. 27867
    Prev
    Next
    INDEX
    Explanations

    code related to resource cleanup and destruction functions

    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
    aeda
    -0.08
     tÆ°Æ¡i
    -0.07
    неÑģ
    -0.07
    ì±ħ
    -0.07
     Dial
    -0.07
     untranslated
    -0.06
    ìĸ´ëĤĺ
    -0.06
    .createClass
    -0.06
     dial
    -0.06
    chez
    -0.06
    POSITIVE LOGITS
    æİī
    0.09
     khá»ıi
    0.07
    _unused
    0.06
    IfExists
    0.06
    indre
    0.06
    all
    0.06
    thag
    0.06
    )dealloc
    0.06
    ucz
    0.06
    ogui
    0.06
    Activations Density 0.045%

    No Known Activations