© 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. 118103
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their related contextual uses

    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
    коÑĢиÑģÑĤ
    -0.09
    IPA
    -0.08
    бÑĢÑı
    -0.08
    ussen
    -0.07
    надлеж
    -0.07
    âĻª↵↵
    -0.07
    etooth
    -0.07
    _IOS
    -0.07
    .yy
    -0.07
    ught
    -0.07
    POSITIVE LOGITS
     cul
    0.08
     most
    0.07
     later
    0.07
    vir
    0.07
     latter
    0.07
    cul
    0.06
    Ùİت
    0.06
    ãĤĤãģ£ãģ¨
    0.06
     occasionally
    0.06
    ud
    0.06
    Activations Density 0.028%

    No Known Activations