© 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. 4157
    Prev
    Next
    INDEX
    Explanations

    references to colors and material types

    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
    Mailer
    -0.06
    279
    -0.06
    ushima
    -0.06
    ellt
    -0.06
    olved
    -0.06
    æ¯Ľ
    -0.06
    itesse
    -0.06
    \Desktop
    -0.06
    684
    -0.05
    bulk
    -0.05
    POSITIVE LOGITS
    .fromString
    0.08
     addCriterion
    0.08
    iskey
    0.07
     color
    0.07
     colour
    0.07
     DÄĽ
    0.07
     neutral
    0.07
    addock
    0.07
    (rawValue
    0.06
    lesc
    0.06
    Activations Density 0.008%

    No Known Activations