© 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. 16350
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their party affiliations

    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
    .documentation
    -0.08
    foundation
    -0.07
    lep
    -0.07
    ообÑĢаз
    -0.06
    ssc
    -0.06
    ì°°
    -0.06
    ç´¹ä»ĭ
    -0.06
    asers
    -0.06
    ãģĤãģĴ
    -0.06
     Circular
    -0.06
    POSITIVE LOGITS
     pist
    0.06
     litt
    0.06
    etooth
    0.06
    evin
    0.06
    696
    0.06
    nbsp
    0.06
     Bruce
    0.06
     Bison
    0.05
    omo
    0.05
    ritt
    0.05
    Activations Density 0.007%

    No Known Activations