© 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 EvalsExportsAPI 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. 59059
    Prev
    Next
    INDEX
    Explanations

    specific guides and lists that help with understanding topics or 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
    LK
    -0.06
     Lor
    -0.06
    ÑĢоÑĩ
    -0.06
    239
    -0.05
    код
    -0.05
     Bes
    -0.05
    1
    -0.05
    inge
    -0.05
    ÑĨо
    -0.05
    phere
    -0.05
    POSITIVE LOGITS
     guide
    0.21
     Guide
    0.19
    -guide
    0.18
    guide
    0.16
    _guide
    0.15
     GUIDE
    0.15
    Guide
    0.15
     guides
    0.15
     Guides
    0.12
    uide
    0.11
    Activations Density 0.060%

    No Known Activations