© 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. 78426
    Prev
    Next
    INDEX
    Explanations

    references to military units or rankings

    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
    liness
    -0.09
    iem
    -0.08
    edly
    -0.08
    views
    -0.07
    ture
    -0.07
    iw
    -0.07
    athers
    -0.07
    table
    -0.07
    list
    -0.07
    orio
    -0.07
    POSITIVE LOGITS
    ughter
    0.09
    0.08
    emp
    0.08
    ity
    0.08
    ulously
    0.08
    arend
    0.07
    quer
    0.07
    eker
    0.07
    erator
    0.07
    UpInside
    0.07
    Activations Density 0.062%

    No Known Activations