© 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 EvalsExportsAPI 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. 85606
    Prev
    Next
    INDEX
    Explanations

    keywords associated with scientific measurements and analysis

    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
     protection
    -0.06
     air
    -0.06
     microscopic
    -0.05
     stake
    -0.05
     rapp
    -0.05
     strands
    -0.05
    kili
    -0.05
    pig
    -0.05
     federal
    -0.05
     arg
    -0.05
    POSITIVE LOGITS
    morph
    0.07
    ewidth
    0.07
    Composer
    0.07
    .SQL
    0.07
    shape
    0.07
     shape
    0.07
     morph
    0.07
    _authentication
    0.07
    ÐIJÑĢÑħÑĸв
    0.07
    ibraries
    0.06
    Activations Density 0.003%

    No Known Activations