© 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. 125762
    Prev
    Next
    INDEX
    Explanations

    references to travel and transportation

    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
    suma
    -0.08
    ataka
    -0.07
    udeau
    -0.07
    andro
    -0.07
     ActionType
    -0.07
    μί
    -0.06
    igar
    -0.06
     semiclass
    -0.06
    hta
    -0.06
    burger
    -0.06
    POSITIVE LOGITS
     passing
    0.08
     between
    0.07
     passage
    0.07
     from
    0.07
     Passing
    0.06
     alike
    0.06
    ê²½
    0.06
    592
    0.06
    625
    0.06
    795
    0.06
    Activations Density 0.033%

    No Known Activations