© 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. 59041
    Prev
    Next
    INDEX
    Explanations

    articles and descriptors indicating quality or uniqueness of items

    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
    å¤ļå°ij
    -0.07
     Instructions
    -0.06
    edi
    -0.06
    aise
    -0.06
    ifax
    -0.06
     hell
    -0.06
    gap
    -0.06
    551
    -0.06
    ofil
    -0.06
    orate
    -0.06
    POSITIVE LOGITS
    permanent
    0.07
     simple
    0.07
     solution
    0.06
    kee
    0.06
     smaller
    0.06
    simple
    0.06
    Coder
    0.06
    yster
    0.06
     Solution
    0.06
    .solution
    0.06
    Activations Density 0.008%

    No Known Activations