© 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. 17-LLAMASCOPE-RES-131K
    11. 2856
    Prev
    Next
    INDEX
    Explanations

    instances of agreement and consensus in discussions about political parties

    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
    leck
    -0.06
    gran
    -0.06
     Wayback
    -0.06
    abwe
    -0.06
    å©·
    -0.05
     :
    -0.05
    QC
    -0.05
    webkit
    -0.05
    -
    -0.05
     Dillon
    -0.05
    POSITIVE LOGITS
    udoku
    0.07
    è¡Ĩ
    0.07
    .sul
    0.07
    زاÙħ
    0.07
    .runners
    0.07
    onaut
    0.07
    ãĤ¹ãĥļ
    0.07
    оÑĢÑĭ
    0.07
    _connected
    0.06
    _Framework
    0.06
    Activations Density 0.007%

    No Known Activations