© 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. 106185
    Prev
    Next
    INDEX
    Explanations

    information related to charter services and their pricing

    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
    readcrumbs
    -0.06
    imbus
    -0.06
    ibble
    -0.06
    292
    -0.06
     correspond
    -0.06
    ivos
    -0.06
    ieri
    -0.06
     Paladin
    -0.06
    .datatables
    -0.06
    åĩ¡
    -0.05
    POSITIVE LOGITS
    ilk
    0.07
     duration
    0.07
    ãĥªãĥ³ãĤ°
    0.07
    duration
    0.07
    ynamo
    0.07
     hin
    0.06
    enity
    0.06
    ¼
    0.06
    cludes
    0.06
     option
    0.06
    Activations Density 0.013%

    No Known Activations