© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28508
    Prev
    Next
    INDEX
    Explanations

    references to the TripAdvisor platform or associated terms

    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
    eren
    -0.08
    abra
    -0.08
    empl
    -0.07
    ancode
    -0.07
    erior
    -0.07
    ibold
    -0.07
    ignum
    -0.07
    istrat
    -0.07
    oplay
    -0.06
    lea
    -0.06
    POSITIVE LOGITS
    licate
    0.11
    ster
    0.08
    ods
    0.08
    .trip
    0.08
     Tri
    0.08
     tri
    0.07
    oli
    0.07
    advisor
    0.07
    wire
    0.07
    per
    0.07
    Activations Density 0.008%

    No Known Activations