© 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. 98152
    Prev
    Next
    INDEX
    Explanations

    different variations of the conjunction "or."

    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
    ibern
    -0.07
    aney
    -0.07
    swick
    -0.06
    gue
    -0.06
    ancies
    -0.06
    quez
    -0.06
    être
    -0.06
    keley
    -0.06
    (strict
    -0.06
    ENDER
    -0.06
    POSITIVE LOGITS
    atak
    0.06
     ``(
    0.06
    ;if
    0.06
     Lambert
    0.06
    842
    0.06
    λÏī
    0.06
    è»
    0.06
     ``
    0.06
    iesz
    0.06
    063
    0.06
    Activations Density 0.009%

    No Known Activations