© 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. 3065
    Prev
    Next
    INDEX
    Explanations

    various structural components or categories within systems

    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
    ryo
    -0.07
    linger
    -0.06
     Baldwin
    -0.06
     hood
    -0.06
    ury
    -0.06
    igt
    -0.06
    ente
    -0.06
     Hutchinson
    -0.06
     league
    -0.05
    jar
    -0.05
    POSITIVE LOGITS
    åĪ¥
    0.08
    ë³Ħ
    0.08
     riêng
    0.08
     Garland
    0.08
    /types
    0.07
    ëłĩê²Į
    0.07
    illance
    0.07
     بÙĨدÛĮ
    0.07
    kazy
    0.07
     ë³Ħ
    0.07
    Activations Density 0.061%

    No Known Activations