© 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. 16049
    Prev
    Next
    INDEX
    Explanations

    discussions around the implications of citizenship and justice in relation to incarcerated individuals and systemic issues

    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
     Záp
    -0.06
    umen
    -0.06
     Aur
    -0.05
     many
    -0.05
     Separate
    -0.05
    nameof
    -0.05
    رسÛĮ
    -0.05
    455
    -0.05
    ÑŁ
    -0.05
     бой
    -0.05
    POSITIVE LOGITS
     convenient
    0.10
     inconvenience
    0.10
     Convenient
    0.09
     inconvenient
    0.09
     Convenience
    0.09
     exped
    0.09
     convenience
    0.08
     conveniently
    0.07
     Exped
    0.07
     handy
    0.07
    Activations Density 0.026%

    No Known Activations