© 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. 17473
    Prev
    Next
    INDEX
    Explanations

    escaped characters in a programming or markup 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
    inn
    -0.07
    ÑĬ
    -0.06
    aepernick
    -0.06
    oda
    -0.06
    ric
    -0.06
    rec
    -0.06
    ¶Į
    -0.06
    SI
    -0.06
    ouro
    -0.06
    \\\\
    -0.06
    POSITIVE LOGITS
    arra
    0.08
    sut
    0.07
    sWith
    0.07
    414
    0.07
    åĤĻ
    0.06
    HQ
    0.06
    æĿ¥çļĦ
    0.06
    s
    0.06
    ude
    0.06
     bid
    0.06
    Activations Density 0.038%

    No Known Activations