© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28733
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage 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
    važ
    -0.07
    èĺŃ
    -0.07
    qus
    -0.07
    ÄĽt
    -0.07
    åĸ
    -0.07
    enha
    -0.07
    orget
    -0.07
    اظ
    -0.07
    woff
    -0.07
    arence
    -0.07
    POSITIVE LOGITS
     Benton
    0.06
     Quartz
    0.06
     thus
    0.06
     therefore
    0.05
    íĤ¹
    0.05
     consequently
    0.05
    ename
    0.05
    abby
    0.05
    774
    0.05
    thus
    0.05
    Activations Density 0.014%

    No Known Activations