© 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. 15-LLAMASCOPE-RES-131K
    11. 87467
    Prev
    Next
    INDEX
    Explanations

    terms related to tourists and tourism

    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
    ï¸ı
    -0.08
    ities
    -0.08
    ed
    -0.07
    cheng
    -0.07
    ding
    -0.07
    ossier
    -0.07
    aises
    -0.07
    een
    -0.06
    eenth
    -0.06
    ness
    -0.06
    POSITIVE LOGITS
    friendly
    0.08
    @dynamic
    0.07
    áž
    0.07
    inclusive
    0.07
    ê¸Ī
    0.07
    /social
    0.07
    -friendly
    0.07
    ipple
    0.07
    peak
    0.07
    åıĶ
    0.07
    Activations Density 0.008%

    No Known Activations