© 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. 121138
    Prev
    Next
    INDEX
    Explanations

    phrases indicating user interest in travel and local culture

    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
    èĴ
    -0.08
     nues
    -0.07
    ertools
    -0.07
    ugu
    -0.07
    enga
    -0.07
    angu
    -0.07
    odos
    -0.07
    ÑģÑıг
    -0.07
    Tracker
    -0.07
    erna
    -0.07
    POSITIVE LOGITS
    736
    0.08
     Qu
    0.07
    Qu
    0.07
    Muon
    0.07
     Ph
    0.06
    628
    0.06
     hoc
    0.06
    an
    0.06
     autoc
    0.06
    687
    0.06
    Activations Density 0.003%

    No Known Activations