© 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. 89750
    Prev
    Next
    INDEX
    Explanations

    terms related to military vehicles and weaponry

    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
    uffman
    -0.07
    iesel
    -0.07
    ndon
    -0.07
    filer
    -0.07
    enburg
    -0.07
    tah
    -0.07
    Aliases
    -0.07
     prostituer
    -0.07
    enek
    -0.07
    presso
    -0.06
    POSITIVE LOGITS
     Mast
    0.06
     pepp
    0.06
     onboard
    0.06
    çŀ
    0.06
     carried
    0.06
    ifax
    0.06
     mounted
    0.06
    ÚĨÛĮ
    0.06
    _mount
    0.06
    utter
    0.06
    Activations Density 0.013%

    No Known Activations