© 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. 81758
    Prev
    Next
    INDEX
    Explanations

    elements related to HTTP request structures and API components

    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
    essay
    -0.07
    cplusplus
    -0.06
    iese
    -0.06
    essen
    -0.06
    ovie
    -0.06
     Sou
    -0.06
     intent
    -0.06
    é«ĺæ¸ħ
    -0.06
     cogn
    -0.06
    azzi
    -0.06
    POSITIVE LOGITS
    gota
    0.07
     ков
    0.06
    aker
    0.06
    akers
    0.06
    ("{\"
    0.06
    ContentView
    0.06
    -render
    0.06
    ÑĤал
    0.06
    unj
    0.06
    .writeln
    0.06
    Activations Density 0.004%

    No Known Activations