© 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. 1596
    Prev
    Next
    INDEX
    Explanations

    references to wearable technology and its features

    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
     retina
    -0.06
     Casting
    -0.06
    estring
    -0.06
    casting
    -0.06
    ÑħÑĢан
    -0.05
     behold
    -0.05
     lo
    -0.05
     captive
    -0.05
    -threatening
    -0.05
    _flip
    -0.05
    POSITIVE LOGITS
     оÑīÑĥÑī
    0.08
    felt
    0.08
    imson
    0.08
    letic
    0.07
    lopedia
    0.07
    lep
    0.07
     felt
    0.07
    iazza
    0.07
     saÄŁlamak
    0.07
    ickle
    0.07
    Activations Density 0.005%

    No Known Activations