© 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. 60281
    Prev
    Next
    INDEX
    Explanations

    references to site verification processes, particularly for social media and search engines

    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
    zÃŃ
    -0.08
    æķ¬
    -0.07
    allon
    -0.07
    AILABLE
    -0.07
    IRTH
    -0.07
    olate
    -0.07
    ëļ
    -0.07
    websocket
    -0.07
    ãĥ¼ãĤº
    -0.07
    cipher
    -0.07
    POSITIVE LOGITS
     meta
    0.07
    <meta
    0.07
     southern
    0.07
    etag
    0.07
    /meta
    0.06
     Robertson
    0.06
     Meta
    0.06
    usk
    0.06
    èľĺèĽĽ
    0.06
     Bing
    0.06
    Activations Density 0.015%

    No Known Activations