© 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 EvalsExportsinterp-engineNEWAPI 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. 70050
    Prev
    Next
    INDEX
    Explanations

    intense emotional reactions to television episodes

    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
    ACHI
    -0.06
    ebra
    -0.06
    owi
    -0.05
    Boot
    -0.05
    lsen
    -0.05
    ÙĦÙĥ
    -0.05
    ocation
    -0.05
    ľ
    -0.05
     legally
    -0.05
    e
    -0.05
    POSITIVE LOGITS
     tonight
    0.09
    uzzi
    0.08
    isol
    0.08
     ìĿ´ë²Ī
    0.07
     episode
    0.07
     Flesh
    0.07
     tod
    0.07
     yesterday
    0.07
    udo
    0.07
     Whisper
    0.07
    Activations Density 0.026%

    No Known Activations