© 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. 4459
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions that connect phrases

    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
    rai
    -0.08
    //{{
    -0.07
    ắt
    -0.07
    ervers
    -0.06
    ampo
    -0.06
     Reception
    -0.06
    æ¡Ī
    -0.06
    orf
    -0.06
    еÑĢв
    -0.06
    erial
    -0.06
    POSITIVE LOGITS
    ayi
    0.07
    igon
    0.07
    ê³ł
    0.06
    imest
    0.06
    cone
    0.06
    ynam
    0.06
    cta
    0.06
     Sands
    0.06
    IGHLIGHT
    0.06
     activeClassName
    0.06
    Activations Density 0.001%

    No Known Activations