© 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. 94298
    Prev
    Next
    INDEX
    Explanations

    phrases signaling definitions and descriptions of abstract concepts

    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
    .Dependency
    -0.10
    _________________↵↵
    -0.09
    \Dependency
    -0.09
     plá
    -0.09
     Xxx
    -0.09
    ınca
    -0.09
    Ñĸз
    -0.09
    _FB
    -0.09
     tô
    -0.09
     lidi
    -0.09
    POSITIVE LOGITS
    â̦↵
    0.09
    ...↵
    0.07
    Âłin
    0.06
    ,
    0.06
    -fontawesome
    0.06
    Âł
    0.06
     exclusively
    0.06
     â̦↵
    0.06
    â̦
    0.05
    ÃĤ
    0.05
    Activations Density 0.825%

    No Known Activations