© 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. 1712
    Prev
    Next
    INDEX
    Explanations

    transit-related information, particularly regarding transportation options and their proximity to locations

    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
    oine
    -0.07
    elsea
    -0.07
    agos
    -0.06
     Chim
    -0.06
    è¶
    -0.06
    hoa
    -0.06
    azor
    -0.06
    otine
    -0.06
    pike
    -0.06
    CHAIN
    -0.06
    POSITIVE LOGITS
    é§ħå¾ĴæŃ©
    0.10
     direct
    0.09
     directly
    0.08
     station
    0.08
     nearest
    0.08
     convenient
    0.07
     å¾ĴæŃ©
    0.07
     непоÑģÑĢед
    0.07
     closest
    0.07
     nearby
    0.07
    Activations Density 0.012%

    No Known Activations