© 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 EvalsExportsinterp-engineNEWAPI 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. 62285
    Prev
    Next
    INDEX
    Explanations

    content related to partnerships and collaborations involving governments or businesses

    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
     massaggi
    -0.07
    ocide
    -0.07
    endir
    -0.07
    lesai
    -0.07
     unlaw
    -0.07
    ooter
    -0.07
    BITS
    -0.07
    ÃŃrk
    -0.07
    ango
    -0.07
    ç®±
    -0.07
    POSITIVE LOGITS
     controversial
    0.21
     controversy
    0.18
     controvers
    0.15
     critics
    0.14
     controversies
    0.14
     Critics
    0.12
     contro
    0.11
     criticism
    0.11
     criticized
    0.11
     polar
    0.11
    Activations Density 0.078%

    No Known Activations