© 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. 85848
    Prev
    Next
    INDEX
    Explanations

    references to specific years, particularly the 1930s and early 1940s

    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
    ooth
    -0.07
    186
    -0.06
    isser
    -0.06
     ecstasy
    -0.06
    159
    -0.06
    skirts
    -0.06
    ADVERTISEMENT
    -0.06
    ä¹ħ
    -0.06
     Reb
    -0.06
    .Formatter
    -0.06
    POSITIVE LOGITS
    anford
    0.07
    ienes
    0.07
    uni
    0.07
    icina
    0.07
    ØŃØ«
    0.06
    sob
    0.06
    adÃŃ
    0.06
    Å¡ak
    0.06
    enko
    0.06
    spender
    0.06
    Activations Density 0.017%

    No Known Activations