© 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. 70791
    Prev
    Next
    INDEX
    Explanations

    numerical values and punctuation that indicate specific information or data formatting

    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
    ĮĴ
    -0.07
    _WRAP
    -0.07
    fmt
    -0.07
    ãģĦãģ¤
    -0.07
    olf
    -0.07
    ulf
    -0.07
    ¦¬
    -0.07
    (Network
    -0.07
    pton
    -0.07
    uto
    -0.07
    POSITIVE LOGITS
     would
    0.11
     wouldn
    0.09
     then
    0.09
     Would
    0.09
     chances
    0.09
    would
    0.09
    then
    0.08
    Would
    0.07
     Wouldn
    0.07
     würde
    0.07
    Activations Density 0.020%

    No Known Activations