© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 129322
    Prev
    Next
    INDEX
    Explanations

    phrases related to conclusions and endings

    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
     inauguration
    -0.06
    egasus
    -0.06
    веÑī
    -0.06
    à¸Ľà¸£à¸°à¸ģ
    -0.06
    vs
    -0.06
    celik
    -0.06
    ucht
    -0.06
    assin
    -0.06
    opoulos
    -0.06
    ÙģاÙĦ
    -0.05
    POSITIVE LOGITS
    /end
    0.10
    -final
    0.09
    =end
    0.09
    indre
    0.08
    ingly
    0.08
    urance
    0.07
    /start
    0.07
    (END
    0.07
    ereco
    0.07
    /footer
    0.07
    Activations Density 0.019%

    No Known Activations