© 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. 87400
    Prev
    Next
    INDEX
    Explanations

    adverbs conveying certainty or degree

    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
    oret
    -0.07
    orem
    -0.07
     indeed
    -0.06
     eventual
    -0.06
     Dont
    -0.06
    женÑĮ
    -0.06
    icken
    -0.06
     Indeed
    -0.06
    oS
    -0.06
    FS
    -0.06
    POSITIVE LOGITS
     there
    0.12
     it
    0.10
     they
    0.09
     we
    0.09
    there
    0.09
     trì
    0.07
    they
    0.07
    QWidget
    0.07
    :\/\/
    0.07
    taÅŁ
    0.07
    Activations Density 0.057%

    No Known Activations