© 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. 84980
    Prev
    Next
    INDEX
    Explanations

    data structures and function definitions related to URLs and context handling in a programming context

    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
     ...(
    -0.07
    619
    -0.06
    ENDOR
    -0.06
     wise
    -0.06
    kid
    -0.06
    zej
    -0.06
    rlen
    -0.06
    olis
    -0.06
     sic
    -0.06
    лиÑĤ
    -0.06
    POSITIVE LOGITS
    ):
    0.08
    ):↵
    0.08
    oleon
    0.07
    .ndarray
    0.07
    )
    0.07
    |int
    0.07
    ):↵↵
    0.06
    suspend
    0.06
    ileo
    0.06
    coder
    0.06
    Activations Density 0.012%

    No Known Activations