© 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. 117931
    Prev
    Next
    INDEX
    Explanations

    programming code structure and formatting elements

    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
     Overlay
    -0.07
    Overlay
    -0.07
     åľ
    -0.07
    zá
    -0.07
    urum
    -0.07
    .unbind
    -0.07
     rempl
    -0.06
    addAction
    -0.06
    inct
    -0.06
    串
    -0.06
    POSITIVE LOGITS
     line
    0.08
    nier
    0.07
     bachelor
    0.06
     Noel
    0.06
    ullet
    0.06
    igos
    0.06
     Line
    0.06
    roe
    0.06
    onne
    0.06
     separate
    0.06
    Activations Density 0.014%

    No Known Activations