© 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. 4042
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations or events and their social media presence

    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
    nees
    -0.06
    mo
    -0.06
     tuz
    -0.06
    OSH
    -0.06
    byn
    -0.06
    ức
    -0.06
    forge
    -0.06
    erland
    -0.06
    afone
    -0.06
    lycer
    -0.06
    POSITIVE LOGITS
    achable
    0.08
     twitter
    0.07
    ↵↵
    0.07
     [@
    0.07
    redient
    0.06
     rub
    0.06
    503
    0.06
     Twitter
    0.06
     xhttp
    0.06
    ubs
    0.06
    Activations Density 0.008%

    No Known Activations