© 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. 73959
    Prev
    Next
    INDEX
    Explanations

    references to claims in a technical or legal context

    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
    hu
    -0.06
    uchar
    -0.06
    isan
    -0.05
     Dong
    -0.05
    nost
    -0.05
    irc
    -0.05
     mouth
    -0.05
     provid
    -0.05
     indeed
    -0.05
     reportedly
    -0.05
    POSITIVE LOGITS
    rames
    0.08
    achuset
    0.08
    isposable
    0.07
    lename
    0.07
    Sand
    0.07
     /*!
    0.07
    ipi
    0.07
    ë§ī
    0.07
    ï¸ı
    0.07
    _ALIAS
    0.07
    Activations Density 0.003%

    No Known Activations