© 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. 15-LLAMASCOPE-RES-131K
    11. 86834
    Prev
    Next
    INDEX
    Explanations

    references to utilities and functionalities of objects or 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
    ifle
    -0.07
    åº
    -0.06
    ï½¥
    -0.06
    imb
    -0.06
    ÙĪزÛĮ
    -0.06
    ntag
    -0.06
    ｡
    -0.06
    {{{
    -0.06
    phin
    -0.06
    oa
    -0.06
    POSITIVE LOGITS
     used
    0.10
    used
    0.09
    çĶ¨äºİ
    0.09
     Used
    0.08
    Used
    0.08
    _used
    0.07
     USED
    0.07
    ovky
    0.07
     also
    0.07
    also
    0.07
    Activations Density 0.020%

    No Known Activations