© 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. 94271
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and delimiters in code

    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
    /**č↵
    -0.07
    ÄĽÅ¾
    -0.07
     Armour
    -0.07
    udeau
    -0.06
    isel
    -0.06
    adol
    -0.06
    Ưá»
    -0.06
    ician
    -0.06
    éĻĨ
    -0.06
     âĢIJ
    -0.06
    POSITIVE LOGITS
    0.10
    elib
    0.07
    eve
    0.07
    0.06
    nbsp
    0.06
    ãĢĢ
    0.06
    æ³³
    0.06
     gist
    0.06
    okt
    0.06
    ork
    0.06
    Activations Density 0.028%

    No Known Activations