© 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. 57771
    Prev
    Next
    INDEX
    Explanations

    references to historical revolutions and their impacts

    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
    å¾ĭ
    -0.09
    anship
    -0.08
    izon
    -0.07
    ppard
    -0.07
    empo
    -0.07
    éĥİ
    -0.07
    ilater
    -0.07
    reten
    -0.07
    olor
    -0.07
    ÎŃα
    -0.06
    POSITIVE LOGITS
     collapse
    0.12
    collapse
    0.09
     collapses
    0.09
     breakdown
    0.09
     collapsing
    0.09
     collapsed
    0.09
     Collapse
    0.08
    -collapse
    0.08
     collaps
    0.08
     downfall
    0.08
    Activations Density 0.058%

    No Known Activations