© 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. 56850
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their contextual usage within sentences

    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
    ilst
    -0.07
    zee
    -0.07
    uel
    -0.07
    ACHI
    -0.07
    gae
    -0.07
    uce
    -0.07
    IDI
    -0.06
    erce
    -0.06
    .named
    -0.06
    ãģĹãģı
    -0.06
    POSITIVE LOGITS
     whose
    0.11
    whose
    0.09
     which
    0.07
    asily
    0.07
    etim
    0.07
    emoc
    0.07
     Jas
    0.06
    åł¡
    0.06
    ANDOM
    0.06
    serter
    0.06
    Activations Density 0.048%

    No Known Activations