© 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. 125695
    Prev
    Next
    INDEX
    Explanations

    emphasized punctuation and expressions of surprise or emphasis

    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
    丸
    -0.07
     thanks
    -0.06
     Lewis
    -0.06
    orre
    -0.06
     sweep
    -0.06
     Boy
    -0.06
    ëĭ
    -0.06
    odd
    -0.05
     Zucker
    -0.05
     cast
    -0.05
    POSITIVE LOGITS
    uml
    0.07
    rette
    0.07
    anner
    0.07
    ANNER
    0.07
    uluk
    0.07
    áºŃt
    0.07
    串
    0.07
    ÑĨеÑģ
    0.07
    Descriptors
    0.06
    λÏĮγ
    0.06
    Activations Density 0.001%

    No Known Activations