© 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. 76420
    Prev
    Next
    INDEX
    Explanations

    references to booking or reservations related to travel or 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
    ndon
    -0.07
    937
    -0.06
    952
    -0.06
     Craw
    -0.06
     Glas
    -0.06
    åĿĤ
    -0.06
    ODO
    -0.06
    amburger
    -0.06
     Arthur
    -0.06
    rough
    -0.06
    POSITIVE LOGITS
    lings
    0.09
    ables
    0.08
    Made
    0.07
    baar
    0.07
     made
    0.07
    able
    0.07
    made
    0.07
    steller
    0.07
    anos
    0.07
    -made
    0.07
    Activations Density 0.004%

    No Known Activations