© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 123577
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and uncertainties

    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
    üf
    -0.07
    ê°ij
    -0.07
    imar
    -0.07
    onis
    -0.07
    orks
    -0.07
    eya
    -0.07
    Ä±ÅŁÄ±k
    -0.07
    TIM
    -0.07
    kud
    -0.06
    ervo
    -0.06
    POSITIVE LOGITS
     always
    0.07
    ÐĴС
    0.06
     familiar
    0.06
     tumblr
    0.06
     Piet
    0.06
     never
    0.06
     Carousel
    0.05
    ç
    0.05
     maybe
    0.05
     Always
    0.05
    Activations Density 0.000%

    No Known Activations