© 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. 84975
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating emphasis or contemplation

    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
    Äĥr
    -0.07
    onga
    -0.07
    ÙģÙĪ
    -0.06
    ابÙĤÙĩ
    -0.06
    odÄĽ
    -0.06
     Mae
    -0.06
    arrison
    -0.06
    alaxy
    -0.06
    rh
    -0.06
    п
    -0.06
    POSITIVE LOGITS
     Volk
    0.07
    åĺĽ
    0.06
    æĻ
    0.06
    ebra
    0.06
    ond
    0.06
    oload
    0.06
     zem
    0.06
    éd
    0.06
    åĿ
    0.06
     lanc
    0.06
    Activations Density 0.004%

    No Known Activations