© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14267
    Prev
    Next
    INDEX
    Explanations

    events or interactions involving notable figures or items (like cars)

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    биÑĤ
    -0.07
     artık
    -0.07
     anymore
    -0.07
    odesk
    -0.07
    zos
    -0.07
    æĹ¢çĦ¶
    -0.07
    ucken
    -0.06
    ammer
    -0.06
     GenerationType
    -0.06
    oki
    -0.06
    POSITIVE LOGITS
     attempted
    0.14
     briefly
    0.13
     attempt
    0.13
     attempts
    0.12
     tried
    0.11
    ä¸Ģ度
    0.11
    attempt
    0.11
    Attempt
    0.11
     Attempt
    0.11
    brief
    0.10
    Activations Density 0.091%

    No Known Activations