© 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. 119267
    Prev
    Next
    INDEX
    Explanations

    terms indicating mixed or contradictory evaluations and experiences

    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
    ë¥´ê³ł
    -0.07
    essler
    -0.07
    uzzi
    -0.07
    Unchecked
    -0.06
     Rarity
    -0.06
    ayet
    -0.06
    .done
    -0.06
    rix
    -0.06
     Roc
    -0.06
    ilenames
    -0.06
    POSITIVE LOGITS
     depending
    0.11
    depending
    0.09
     Depending
    0.08
    mixed
    0.07
    Depending
    0.07
     Depends
    0.07
     mixed
    0.07
     contradictory
    0.07
    /conf
    0.07
     balance
    0.07
    Activations Density 0.019%

    No Known Activations