© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128324
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequency

    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
    rint
    -0.07
    _EOL
    -0.06
    echan
    -0.06
    /close
    -0.06
    chan
    -0.06
     versus
    -0.06
    elly
    -0.06
    ÐĶÐļ
    -0.06
    ially
    -0.06
    iti
    -0.06
    POSITIVE LOGITS
    apiro
    0.07
    ichert
    0.07
    -valu
    0.07
     ãģı
    0.06
    ãģ£ãģı
    0.06
    uld
    0.06
    incer
    0.06
    .fast
    0.06
    Inc
    0.06
    udic
    0.06
    Activations Density 0.007%

    No Known Activations