© 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. 83724
    Prev
    Next
    INDEX
    Explanations

    code elements related to programming and functionality within a software 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
    /people
    -0.07
    alte
    -0.07
    /us
    -0.06
     Gul
    -0.06
    /by
    -0.06
    cestor
    -0.06
    riel
    -0.06
    rador
    -0.06
    rame
    -0.05
    liga
    -0.05
    POSITIVE LOGITS
    edException
    0.10
     کردÙĨ
    0.09
    ÂŃing
    0.09
    /disable
    0.08
     vess
    0.07
    edList
    0.07
    pping
    0.07
    ierung
    0.07
    844
    0.07
    able
    0.07
    Activations Density 0.161%

    No Known Activations