© 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. 128879
    Prev
    Next
    INDEX
    Explanations

    strongly emphasized assertions or commitments

    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
    oker
    -0.07
     ем
    -0.07
    UPI
    -0.06
    é¤Ĭ
    -0.06
    etz
    -0.06
    omba
    -0.06
    اگ
    -0.06
    zon
    -0.06
     Rica
    -0.06
    á»ĵn
    -0.06
    POSITIVE LOGITS
    ament
    0.07
    ness
    0.07
     grasp
    0.07
    /loose
    0.07
    iously
    0.07
    leck
    0.06
    ìĪł
    0.06
     footing
    0.06
     belonging
    0.06
     Fir
    0.06
    Activations Density 0.009%

    No Known Activations