© 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. 39174
    Prev
    Next
    INDEX
    Explanations

    layers and preparation steps in a recipe

    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
    illum
    -0.07
    ancellable
    -0.06
     tit
    -0.06
    lk
    -0.06
    rame
    -0.06
    RAL
    -0.06
    -turned
    -0.06
    ÙĪاء
    -0.06
     Stap
    -0.06
    _SELF
    -0.06
    POSITIVE LOGITS
     layer
    0.11
     layers
    0.08
    Layer
    0.08
    layer
    0.07
     Layer
    0.07
    .layer
    0.07
    -abs
    0.07
    _layer
    0.07
     Layers
    0.07
    ỳ
    0.07
    Activations Density 0.038%

    No Known Activations