© 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. 15-LLAMASCOPE-RES-131K
    11. 103161
    Prev
    Next
    INDEX
    Explanations

    contrastive phrases that highlight exceptions or limitations in a discussion

    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
    æŀĿ
    -0.07
    oice
    -0.07
    Soon
    -0.07
     moc
    -0.06
    ookie
    -0.06
    ervations
    -0.06
    .scalablytyped
    -0.06
    wers
    -0.06
     Soon
    -0.06
     Malone
    -0.06
    POSITIVE LOGITS
    uis
    0.06
     no
    0.06
    NAL
    0.06
    Ïģκε
    0.06
     others
    0.06
    ht
    0.06
     circular
    0.06
     otras
    0.06
    IVED
    0.06
    utor
    0.06
    Activations Density 0.020%

    No Known Activations