© 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. 125528
    Prev
    Next
    INDEX
    Explanations

    references to families, businesses, and community structures

    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
    ...↵
    -0.07
    -0.07
     Le
    -0.06
     ·
    -0.06
    âĢ¦↵
    -0.06
     ...↵
    -0.06
    ↵
    -0.06
    :
    -0.06
    -than
    -0.05
    https
    -0.05
    POSITIVE LOGITS
    wide
    0.14
    -wide
    0.13
    Wide
    0.10
    -owned
    0.10
    ฯ
    0.09
     wide
    0.09
    edia
    0.09
    ouser
    0.09
    γγ
    0.08
    bulan
    0.08
    Activations Density 0.028%

    No Known Activations