© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88344
    Prev
    Next
    INDEX
    Explanations

    method and function signatures related to table view and hyperlink handling in programming contexts

    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
    ounder
    -0.07
    reon
    -0.07
    utin
    -0.07
    ebin
    -0.07
    cke
    -0.07
    reeNode
    -0.07
    entar
    -0.07
    gency
    -0.07
    /XMLSchema
    -0.07
    prene
    -0.07
    POSITIVE LOGITS
    adora
    0.07
    506
    0.07
     Sang
    0.06
    379
    0.06
    ÑĸÑģно
    0.06
    Facade
    0.06
    ju
    0.06
     Goodman
    0.06
    XR
    0.06
    ì§Ħ
    0.06
    Activations Density 0.002%

    No Known Activations