© 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. 72468
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate excitement or urgency

    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
     ed
    -0.06
     target
    -0.06
    uilder
    -0.05
    ittal
    -0.05
    ime
    -0.05
     Destination
    -0.05
     autom
    -0.05
     formal
    -0.05
     skip
    -0.05
     crud
    -0.05
    POSITIVE LOGITS
    maal
    0.08
    isons
    0.07
    alin
    0.07
    raç
    0.07
    umd
    0.07
    tep
    0.07
     Eig
    0.07
    .Features
    0.07
    alı
    0.07
    !č↵
    0.06
    Activations Density 0.023%

    No Known Activations