© 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 EvalsExportsAPI 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. 59253
    Prev
    Next
    INDEX
    Explanations

    activities related to guided tours and travel experiences

    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
    alama
    -0.09
    ableOpacity
    -0.08
    idy
    -0.07
    clr
    -0.07
    .EventHandler
    -0.07
    виÑĤ
    -0.07
     ydk
    -0.07
    iosper
    -0.07
    çĽijåIJ¬é¡µéĿ¢
    -0.07
    .Features
    -0.07
    POSITIVE LOGITS
     local
    0.08
     authentic
    0.07
     locally
    0.07
     hands
    0.07
    auth
    0.07
    ogie
    0.06
     locals
    0.06
     sam
    0.06
     typical
    0.06
     Local
    0.06
    Activations Density 0.021%

    No Known Activations