© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5818
    Prev
    Next
    INDEX
    Explanations

    keywords related to optical equipment and the military context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    479
    -0.06
    .scal
    -0.06
     Inventory
    -0.06
    883
    -0.06
     NFC
    -0.06
    868
    -0.06
     Storage
    -0.06
     cục
    -0.05
     elastic
    -0.05
    865
    -0.05
    POSITIVE LOGITS
    finder
    0.09
    -mount
    0.09
     mount
    0.08
    SPORT
    0.08
    Sports
    0.08
     hunting
    0.08
     Sport
    0.07
     shooters
    0.07
     Sports
    0.07
    _mount
    0.07
    Activations Density 0.002%

    No Known Activations