© 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. 73600
    Prev
    Next
    INDEX
    Explanations

    information related to flight schedules and travel services

    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
    ario
    -0.06
    ormsg
    -0.06
    illo
    -0.06
    /=
    -0.06
     interior
    -0.06
    asil
    -0.06
     ucwords
    -0.06
     hors
    -0.06
     zip
    -0.06
    å±¥
    -0.06
    POSITIVE LOGITS
    ç·
    0.07
    elper
    0.07
    .Route
    0.07
     route
    0.06
    ushman
    0.06
    uD
    0.06
    vá
    0.06
    }elseif
    0.06
     Direct
    0.06
    itespace
    0.06
    Activations Density 0.010%

    No Known Activations