© 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. 14834
    Prev
    Next
    INDEX
    Explanations

    references to software updates and installation 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
     Brennan
    -0.07
     intens
    -0.07
    ç©´
    -0.06
     Crate
    -0.06
    chner
    -0.06
     Bracket
    -0.06
    ศาสà¸ķร
    -0.06
     inher
    -0.06
    каÑģ
    -0.06
    ITTER
    -0.06
    POSITIVE LOGITS
     curl
    0.06
    obar
    0.06
    curl
    0.06
    .inf
    0.06
     bullet
    0.06
     downloads
    0.06
    Downloading
    0.06
     downloading
    0.06
    ÙĪÙĦÙĪ
    0.06
     download
    0.06
    Activations Density 0.003%

    No Known Activations