© 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. 62356
    Prev
    Next
    INDEX
    Explanations

    concepts related to duality or multiple components within a system

    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
     tie
    -0.06
    oti
    -0.06
     Jacqu
    -0.06
    elle
    -0.06
    elsen
    -0.06
    лада
    -0.06
    ebe
    -0.06
    jn
    -0.06
    mp
    -0.06
     Tie
    -0.06
    POSITIVE LOGITS
    —one
    0.10
    åĪĨåĪ«
    0.10
     one
    0.09
    à¹Į:
    0.08
    (one
    0.08
    ãģĨãģ¡
    0.08
    :first
    0.08
    ä¸Ģ页
    0.08
     separated
    0.08
    :
    0.07
    Activations Density 0.038%

    No Known Activations