© 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. 15068
    Prev
    Next
    INDEX
    Explanations

    references to display issues and damage in screens

    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
    Ïħκ
    -0.06
     Wilde
    -0.06
    åŁĭ
    -0.06
     marc
    -0.06
    åĵ
    -0.06
    vox
    -0.06
     bulky
    -0.06
    mlink
    -0.05
    [".
    -0.05
     Boulevard
    -0.05
    POSITIVE LOGITS
     artifacts
    0.08
     artifact
    0.07
    ãģ¡ãĤī
    0.07
    ipeg
    0.07
    dere
    0.06
     Král
    0.06
    erro
    0.06
    ÅĻet
    0.06
    rede
    0.06
    λμ
    0.06
    Activations Density 0.015%

    No Known Activations