© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97610
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequencies in the document

    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
    iaux
    -0.07
    <Scalar
    -0.07
    istrovstvÃŃ
    -0.07
    INVAL
    -0.07
    ÙģضÙĦ
    -0.07
     Ending
    -0.07
    laus
    -0.07
    reso
    -0.07
    asion
    -0.07
    _OW
    -0.07
    POSITIVE LOGITS
    enberg
    0.06
    bis
    0.06
    enz
    0.06
    enza
    0.06
    sad
    0.06
     intrigue
    0.05
    ieu
    0.05
     carp
    0.05
     domic
    0.05
    QRS
    0.05
    Activations Density 0.003%

    No Known Activations