© 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. 62792
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to programming and data handling in software development

    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
    uth
    -0.08
    ores
    -0.07
    antz
    -0.06
    .FileWriter
    -0.06
    utive
    -0.06
     printers
    -0.06
     Farrell
    -0.06
    rl
    -0.06
    å®ľ
    -0.06
    673
    -0.06
    POSITIVE LOGITS
    Adobe
    0.10
     Adobe
    0.10
    -flash
    0.08
    _flash
    0.08
     URLRequest
    0.07
     Flash
    0.07
     flash
    0.07
    .habbo
    0.07
    Vars
    0.07
     Colorado
    0.07
    Activations Density 0.054%

    No Known Activations