© 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. 56623
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and attractions, especially beaches

    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
    .cloudflare
    -0.08
    oÄŁ
    -0.07
    //{{
    -0.07
    unnel
    -0.07
    าà¸į
    -0.07
    ë¹Ļ
    -0.07
    ź
    -0.07
    abyrinth
    -0.07
    (æľ¨
    -0.07
     doma
    -0.07
    POSITIVE LOGITS
     beaches
    0.09
     beach
    0.09
     Beach
    0.08
     sand
    0.07
     Sand
    0.07
     bay
    0.07
     sands
    0.07
    arkan
    0.06
     location
    0.06
    /div
    0.06
    Activations Density 0.012%

    No Known Activations