© 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. 78340
    Prev
    Next
    INDEX
    Explanations

    expressions of negation or contrast

    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
    aight
    -0.07
    isphere
    -0.07
    ancement
    -0.07
    .nano
    -0.06
    nip
    -0.06
    .where
    -0.06
    atham
    -0.06
    _NEED
    -0.06
    /sdk
    -0.06
    ="__
    -0.06
    POSITIVE LOGITS
     attempt
    0.07
     use
    0.07
    _defaults
    0.07
    htdocs
    0.06
    741
    0.06
    Ãło
    0.06
    ť
    0.06
     try
    0.06
    attempt
    0.06
     set
    0.06
    Activations Density 0.012%

    No Known Activations