© 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. 126065
    Prev
    Next
    INDEX
    Explanations

    phrases about personal freedom and ownership

    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
    etti
    -0.08
    edo
    -0.08
    .vertx
    -0.08
    inke
    -0.07
    odon
    -0.07
    imple
    -0.07
    itzer
    -0.07
    ãĤ«ãĥ¼
    -0.07
    otti
    -0.07
    olt
    -0.07
    POSITIVE LOGITS
     Flex
    0.08
     Vern
    0.07
     Hacker
    0.07
     ï¿¥
    0.07
    Flex
    0.06
     flexible
    0.06
     Flexible
    0.06
     flex
    0.06
    Flexible
    0.06
     Coal
    0.06
    Activations Density 0.001%

    No Known Activations