© 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 EvalsExportsinterp-engineNEWAPI 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. 30982
    Prev
    Next
    INDEX
    Explanations

    references to flights and air travel

    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
    ped
    -0.07
     FLASH
    -0.06
     NET
    -0.06
     words
    -0.06
     extreme
    -0.06
     ful
    -0.06
     drivers
    -0.06
     NOM
    -0.06
    gin
    -0.06
     Ring
    -0.06
    POSITIVE LOGITS
    .synthetic
    0.08
    داÙĨ
    0.08
    .Toolkit
    0.07
    iParam
    0.07
    ugin
    0.07
    urm
    0.07
     GetHashCode
    0.07
     Burb
    0.07
    871
    0.07
    TouchUpInside
    0.07
    Activations Density 0.018%

    No Known Activations