© 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. 94320
    Prev
    Next
    INDEX
    Explanations

    references to web framework components and their methods

    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
    antz
    -0.06
     Dün
    -0.06
    ï¼ģï¼ģ↵↵
    -0.06
     RT
    -0.06
    .FontStyle
    -0.06
    ÅĻen
    -0.06
    ãĤĥ
    -0.06
     rocker
    -0.06
    IME
    -0.06
    uddle
    -0.06
    POSITIVE LOGITS
    eson
    0.07
     Abyss
    0.06
    illis
    0.06
    ìĹIJê²Į
    0.06
    aby
    0.06
    536
    0.06
    deck
    0.06
    kins
    0.06
    elerik
    0.06
    andr
    0.06
    Activations Density 0.010%

    No Known Activations