© 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. 124729
    Prev
    Next
    INDEX
    Explanations

    references to transportation infrastructure

    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
    wand
    -0.08
    nova
    -0.07
    ffa
    -0.07
    úsqueda
    -0.07
    MEA
    -0.07
    rieve
    -0.07
    jec
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    ãĥ¼ãĤ¸
    -0.07
    ãĥªãĤ«
    -0.07
    POSITIVE LOGITS
     connectors
    0.06
     access
    0.06
    inen
    0.06
    achs
    0.06
     connect
    0.06
     connector
    0.06
     connections
    0.06
    orthy
    0.06
     connects
    0.06
    -connect
    0.06
    Activations Density 0.010%

    No Known Activations