© 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. 56685
    Prev
    Next
    INDEX
    Explanations

    instances of commas in the text

    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
    but
    -0.09
     but
    -0.08
    ï¼Įä½Ĩ
    -0.08
     whom
    -0.08
     pero
    -0.08
     however
    -0.07
    ï¼Įä½Ĩæĺ¯
    -0.07
     nhÆ°ng
    -0.07
    ...↵
    -0.07
    ãģĬãĤĬ
    -0.06
    POSITIVE LOGITS
     albeit
    0.07
    uhe
    0.07
     cul
    0.06
    ubah
    0.06
    aÄį
    0.06
    otas
    0.06
     sez
    0.06
    teki
    0.06
    iasi
    0.06
    izu
    0.06
    Activations Density 0.035%

    No Known Activations