© 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. 76475
    Prev
    Next
    INDEX
    Explanations

    phrases related to user reviews and travel accommodations

    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
    atat
    -0.06
     Crunch
    -0.06
    ewan
    -0.06
     vive
    -0.06
     Ellis
    -0.06
     Sand
    -0.06
     Outs
    -0.06
     Mare
    -0.06
    igon
    -0.06
    mares
    -0.06
    POSITIVE LOGITS
    ůl
    0.08
    ÄĽÅ¾
    0.07
    gem
    0.07
    ymm
    0.07
    chter
    0.07
    ï¼ļ↵
    0.07
    affle
    0.06
    imu
    0.06
     podrob
    0.06
    059
    0.06
    Activations Density 0.027%

    No Known Activations