© 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. 94634
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotions or deep feelings

    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
    itung
    -0.09
    eses
    -0.07
    alink
    -0.07
    emony
    -0.07
    ascript
    -0.07
    icans
    -0.07
    inson
    -0.07
     zas
    -0.07
    eah
    -0.07
    κή
    -0.07
    POSITIVE LOGITS
     intensity
    0.07
     intense
    0.06
    eel
    0.06
    248
    0.06
    ucci
    0.06
    ella
    0.06
    Äħ
    0.05
    mp
    0.05
    Peer
    0.05
     cropped
    0.05
    Activations Density 0.006%

    No Known Activations