© 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. 60389
    Prev
    Next
    INDEX
    Explanations

    names of historical or influential figures

    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
    amer
    -0.08
    DonaldTrump
    -0.07
    afx
    -0.07
    AMED
    -0.07
    arus
    -0.07
     ÑĤва
    -0.07
    DataExchange
    -0.07
    baugh
    -0.07
    Ä±ÅŁÄ±k
    -0.07
    amedi
    -0.07
    POSITIVE LOGITS
     brief
    0.07
     roles
    0.07
     opposed
    0.07
     contributed
    0.06
     arrest
    0.06
     opposing
    0.06
     as
    0.06
     moderate
    0.06
     instrument
    0.06
    ena
    0.06
    Activations Density 0.029%

    No Known Activations