© 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. 128172
    Prev
    Next
    INDEX
    Explanations

    references to previous comments and discussions in a conversational context

    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
    .scalablytyped
    -0.08
     ëĭ¤ìļ´ë°Ľê¸°
    -0.08
    ibbon
    -0.07
    erno
    -0.07
    iox
    -0.07
    LAR
    -0.07
    íķĻëħĦëıĦ
    -0.07
    elter
    -0.07
    LC
    -0.07
     Ðijез
    -0.06
    POSITIVE LOGITS
     thread
    0.09
     post
    0.09
     earlier
    0.08
     threads
    0.08
     reply
    0.08
    Reply
    0.07
     posts
    0.07
     Thread
    0.07
     previous
    0.07
     Reply
    0.07
    Activations Density 0.026%

    No Known Activations