© 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. 62020
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to software development processes

    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
     Clearance
    -0.06
    icit
    -0.06
     Fur
    -0.06
     part
    -0.06
    é¢ĺ
    -0.06
    bpp
    -0.06
    بط
    -0.06
    entes
    -0.06
    اÙħÙĩ
    -0.05
    ja
    -0.05
    POSITIVE LOGITS
    tar
    0.08
     tar
    0.07
    SHA
    0.07
    _DOWNLOAD
    0.07
    suffix
    0.07
     releases
    0.07
    tog
    0.07
    mirror
    0.07
    TargetException
    0.07
    inja
    0.07
    Activations Density 0.010%

    No Known Activations