© 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. 77358
    Prev
    Next
    INDEX
    Explanations

    references to specific platforms and devices for software installation

    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
     Rab
    -0.07
    byt
    -0.07
    rab
    -0.07
    inan
    -0.07
    ERT
    -0.07
    pak
    -0.06
     Tweets
    -0.06
     eBooks
    -0.06
    Ä©a
    -0.06
    об
    -0.06
    POSITIVE LOGITS
    elik
    0.07
     باÙĦا
    0.06
    patible
    0.06
    jd
    0.06
    iven
    0.06
     metros
    0.06
    LIK
    0.06
     segment
    0.06
     metro
    0.05
     Bened
    0.05
    Activations Density 0.007%

    No Known Activations