© 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. 74298
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting indicators in technical documentation

    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
    urd
    -0.07
    erts
    -0.06
    cent
    -0.06
     vej
    -0.06
    mentation
    -0.06
    gii
    -0.06
    ãĤĪãģĨãģª
    -0.06
    ient
    -0.06
    μη
    -0.06
    :*
    -0.06
    POSITIVE LOGITS
     بÙĪابة
    0.10
    ãĥ»ãĥ»ãĥ»↵↵
    0.08
     ...↵↵↵↵
    0.07
    keh
    0.07
    ocker
    0.07
    ãĥŃãĥ¼
    0.07
     <!--[
    0.07
    iteDatabase
    0.07
    OperationException
    0.07
    Neutral
    0.07
    Activations Density 0.015%

    No Known Activations