© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56044
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and the accompanying phrases that convey context, particularly quotations and dialog

    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
    etag
    -0.07
    лÑĸд
    -0.07
    _dot
    -0.07
     kolej
    -0.07
    dü
    -0.07
    cak
    -0.07
     unut
    -0.07
    OOT
    -0.07
    رش
    -0.07
    _simps
    -0.07
    POSITIVE LOGITS
     "
    0.08
     '
    0.07
     «
    0.07
     "[
    0.06
    undi
    0.06
     “
    0.06
     \"
    0.06
     '[
    0.06
     half
    0.06
     ‘
    0.06
    Activations Density 0.005%

    No Known Activations