© 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. 9-LLAMASCOPE-RES-131K
    11. 97365
    Prev
    Next
    INDEX
    Explanations

    mentions of travel, accommodations, or tourism activities

    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
     busy
    -0.07
    asal
    -0.07
    AxisAlignment
    -0.06
    isse
    -0.06
    busy
    -0.06
    å¿Ļ
    -0.06
     busiest
    -0.06
    phy
    -0.06
     appearances
    -0.06
    اÙĩر
    -0.06
    POSITIVE LOGITS
     Interr
    0.07
    çļĦåľ°
    0.07
    rack
    0.07
     travel
    0.06
     اÙĦرØŃ
    0.06
    Instr
    0.06
    Resolution
    0.06
     overlays
    0.06
     Bucket
    0.06
     Marseille
    0.06
    Activations Density 0.336%

    No Known Activations