© 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. 79958
    Prev
    Next
    INDEX
    Explanations

    references to various championships and competitive events

    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
    ῶ
    -0.08
    .Transactional
    -0.07
     Lah
    -0.07
    lobal
    -0.07
    StateException
    -0.07
    azzo
    -0.07
    ossa
    -0.07
    -fit
    -0.06
    ±
    -0.06
    obile
    -0.06
    POSITIVE LOGITS
     link
    0.09
     links
    0.08
    éĵ¾æİ¥
    0.07
    _link
    0.07
    /link
    0.07
    (link
    0.07
    Links
    0.07
    links
    0.06
    link
    0.06
    -link
    0.06
    Activations Density 0.002%

    No Known Activations