© 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. 107516
    Prev
    Next
    INDEX
    Explanations

    terms related to tracking and locating devices

    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
    761
    -0.07
     Williams
    -0.06
     @}
    -0.06
    layan
    -0.06
    spb
    -0.06
    uchos
    -0.06
    æıĴ
    -0.06
    ì¼ĵ
    -0.06
    (æ°´
    -0.06
     refer
    -0.06
    POSITIVE LOGITS
     lost
    0.07
    help
    0.07
     Recovery
    0.07
    ToEnd
    0.07
     help
    0.07
     Distance
    0.07
     recovery
    0.06
     Recover
    0.06
     Lost
    0.06
     distances
    0.06
    Activations Density 0.004%

    No Known Activations