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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 83099
    Prev
    Next
    INDEX
    Explanations

    terms related to flight information and travel booking

    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
    .scalablytyped
    -0.07
    IEWS
    -0.07
     Ness
    -0.07
    shipping
    -0.07
    etary
    -0.07
     Cruiser
    -0.07
    .require
    -0.06
     shipping
    -0.06
    styles
    -0.06
     Pak
    -0.06
    POSITIVE LOGITS
    çıŃ
    0.07
    izu
    0.07
     statuses
    0.06
    _ie
    0.06
     bunk
    0.06
     çı
    0.06
     tá»ij
    0.06
    uin
    0.06
    uÄį
    0.06
    rq
    0.06
    Activations Density 0.002%

    No Known Activations