© 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. 2267
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software and programming functionality

    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
    ¶ģ
    -0.07
     kontakte
    -0.07
    _cmos
    -0.07
    ewis
    -0.07
    λιά
    -0.07
    hton
    -0.07
    «ĺ
    -0.07
    etre
    -0.07
    ittest
    -0.07
    .firebaseapp
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.08
    elles
    0.06
    ekler
    0.06
    _PS
    0.06
    etc
    0.06
     Commons
    0.05
     ps
    0.05
    .
    0.05
     Premium
    0.05
    ps
    0.05
    Activations Density 0.009%

    No Known Activations