© 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. 17-LLAMASCOPE-RES-131K
    11. 2791
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations

    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
    748
    -0.06
     Roc
    -0.06
     len
    -0.06
     DISTRIBUT
    -0.05
     resid
    -0.05
     Slee
    -0.05
     Golf
    -0.05
     sleeper
    -0.05
     bow
    -0.05
     roc
    -0.05
    POSITIVE LOGITS
     stock
    0.09
    -stock
    0.07
    stock
    0.07
     drift
    0.07
     Mark
    0.07
     Orn
    0.07
    bs
    0.07
    éŃĤ
    0.07
     umbrella
    0.07
     Stock
    0.07
    Activations Density 0.367%

    No Known Activations