© 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. 107272
    Prev
    Next
    INDEX
    Explanations

    phrases and elements related to visual storytelling and impressive imagery

    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
    gnore
    -0.07
    먼
    -0.07
    ongs
    -0.06
    endi
    -0.06
    camp
    -0.06
     aktar
    -0.06
    brush
    -0.06
    icates
    -0.06
    hurst
    -0.06
    اÙĤ
    -0.06
    POSITIVE LOGITS
     display
    0.07
    zel
    0.07
    apiro
    0.07
    Ìģ
    0.07
    evin
    0.07
    "display
    0.07
    -wall
    0.07
    -display
    0.07
    urgeon
    0.07
    елен
    0.06
    Activations Density 0.019%

    No Known Activations