© 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. 69488
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, events, and descriptions related to travel and adventure

    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
     plastic
    -0.07
     Berm
    -0.07
    èī¦
    -0.07
    ullet
    -0.07
     Plastic
    -0.07
    shima
    -0.07
     island
    -0.06
    raft
    -0.06
     maduras
    -0.06
     islands
    -0.06
    POSITIVE LOGITS
     travellers
    0.10
     travelling
    0.09
     travelers
    0.09
     traveling
    0.09
     travel
    0.09
    æĹħè¡Į
    0.09
     traveler
    0.09
     caravan
    0.09
     Inn
    0.08
     traveller
    0.08
    Activations Density 0.056%

    No Known Activations