© 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. 15-LLAMASCOPE-RES-131K
    11. 86370
    Prev
    Next
    INDEX
    Explanations

    information related to research projects and their characteristics

    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
    istrovstvÃŃ
    -0.07
    æīĢæľī
    -0.07
    .xtext
    -0.07
    ereo
    -0.07
    rone
    -0.07
     Flake
    -0.07
    è¨Ī
    -0.07
    ska
    -0.07
     же
    -0.07
    ubby
    -0.07
    POSITIVE LOGITS
     or
    0.10
     themselves
    0.09
     either
    0.09
     directly
    0.08
    //{{
    0.07
     или
    0.07
    æĪĸ
    0.07
    ocab
    0.07
     Either
    0.07
     hoặc
    0.06
    Activations Density 0.076%

    No Known Activations