© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 128423
    Prev
    Next
    INDEX
    Explanations

    references to announcements and decisions made by companies and organizations

    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
     Boutique
    -0.08
     Becker
    -0.07
     erotik
    -0.07
    .weixin
    -0.07
     erotici
    -0.07
     boutique
    -0.07
    ÃŃrk
    -0.07
    à¥įवर
    -0.07
    łģ
    -0.06
    ockets
    -0.06
    POSITIVE LOGITS
     announcement
    0.10
     announced
    0.10
     plans
    0.10
     announce
    0.10
     plan
    0.09
    ann
    0.09
     annon
    0.08
    announcement
    0.08
    will
    0.08
    Ann
    0.07
    Activations Density 0.031%

    No Known Activations