© 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. 85320
    Prev
    Next
    INDEX
    Explanations

    situations involving accidents or falls

    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
    ÏĪη
    -0.07
    xmm
    -0.07
    ilogy
    -0.07
     spoj
    -0.07
    ladu
    -0.07
    orges
    -0.07
    Å¡il
    -0.07
     Gül
    -0.07
    /WebAPI
    -0.06
     Fant
    -0.06
    POSITIVE LOGITS
     fall
    0.09
     fallen
    0.09
     Falling
    0.08
    fall
    0.08
     stability
    0.08
     falls
    0.08
     balance
    0.08
     FALL
    0.07
    _FALL
    0.07
     fell
    0.07
    Activations Density 0.056%

    No Known Activations