© 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. 108212
    Prev
    Next
    INDEX
    Explanations

    references to items or products available for sale

    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
     mari
    -0.06
    iner
    -0.06
    меÑĤÑĮ
    -0.06
     might
    -0.06
     cog
    -0.06
    vious
    -0.06
    ings
    -0.06
    ingle
    -0.06
     inj
    -0.06
     expelled
    -0.06
    POSITIVE LOGITS
    åĿĩ
    0.08
    sik
    0.08
     trừ
    0.08
    onz
    0.07
    issional
    0.07
    ÐŀÐł
    0.07
    avana
    0.07
    ascus
    0.07
    -Sah
    0.07
    unpack
    0.07
    Activations Density 0.016%

    No Known Activations