© 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. 77293
    Prev
    Next
    INDEX
    Explanations

    references to documentation and technical guides

    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
    azz
    -0.07
    ounge
    -0.06
    ourse
    -0.06
     McA
    -0.06
    eka
    -0.06
     Hob
    -0.06
     tat
    -0.06
     Paleo
    -0.06
    æĮ¯ãĤĬ
    -0.05
     Mori
    -0.05
    POSITIVE LOGITS
    uments
    0.08
    oshi
    0.07
    iteli
    0.07
     addCriterion
    0.07
    ůvod
    0.07
    303
    0.07
     Tos
    0.07
    rier
    0.07
    heits
    0.07
    aines
    0.07
    Activations Density 0.000%

    No Known Activations