© 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. 126536
    Prev
    Next
    INDEX
    Explanations

    information related to distances and travel queries

    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
     improving
    -0.07
    alen
    -0.06
    inger
    -0.06
     improve
    -0.06
    åĿ¡
    -0.06
     Schwe
    -0.06
    lor
    -0.06
    ln
    -0.06
     Lyn
    -0.06
     improved
    -0.06
    POSITIVE LOGITS
    estar
    0.07
    isposable
    0.07
    aç
    0.07
    rome
    0.07
    ahren
    0.07
    UpdateTime
    0.07
    ponsive
    0.07
    #
    0.06
    RIX
    0.06
    WithIdentifier
    0.06
    Activations Density 0.002%

    No Known Activations