© 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. 29248
    Prev
    Next
    INDEX
    Explanations

    names that are associated with sports or athletic achievements

    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
    eras
    -0.08
    ëģĶ
    -0.07
    oken
    -0.07
    inkel
    -0.07
    ëĭ¤ê°Ģ
    -0.07
    ors
    -0.07
    ÙĪÙħاÙĨ
    -0.07
    oko
    -0.07
    ingt
    -0.06
    gui
    -0.06
    POSITIVE LOGITS
    Ø©
    0.09
    Ùħ
    0.08
    hoff
    0.07
    ucle
    0.07
     latter
    0.07
    eer
    0.07
    yang
    0.07
    eting
    0.07
    .forRoot
    0.06
    ------------------------------------------------------------------------------------------------
    0.06
    Activations Density 0.016%

    No Known Activations