© 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. 88473
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically the comma

    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
     Nack
    -0.07
    orro
    -0.07
    ework
    -0.07
    imizer
    -0.07
    ::_
    -0.07
    ego
    -0.07
    producer
    -0.07
    ãĥĭãĤ¢
    -0.06
    igel
    -0.06
    _EOL
    -0.06
    POSITIVE LOGITS
     states
    0.07
     Novel
    0.07
     Ih
    0.06
     novel
    0.06
    addir
    0.06
    resco
    0.06
    .scalablytyped
    0.06
    annis
    0.06
     weird
    0.06
     whilst
    0.06
    Activations Density 0.000%

    No Known Activations