© 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. 29392
    Prev
    Next
    INDEX
    Explanations

    intense emotional experiences and moments of excitement

    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
    è¦
    -0.07
    æĪ»
    -0.07
    ambi
    -0.06
    rž
    -0.06
    oris
    -0.06
    ndx
    -0.06
    orch
    -0.06
    .twig
    -0.06
    crud
    -0.06
    utra
    -0.06
    POSITIVE LOGITS
     prepar
    0.08
     Pump
    0.08
     ramp
    0.08
     pre
    0.08
     prim
    0.08
     pump
    0.08
    èµ·
    0.07
     buildup
    0.07
     rev
    0.07
     build
    0.07
    Activations Density 0.071%

    No Known Activations