© 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. 69123
    Prev
    Next
    INDEX
    Explanations

    phrases indicating capability or completion of actions

    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
    estre
    -0.08
     à¸łà¸²à¸©
    -0.08
    uters
    -0.07
    .createServer
    -0.07
    HOOK
    -0.07
    teri
    -0.07
    sak
    -0.07
    ãn
    -0.07
    òi
    -0.07
    oust
    -0.07
    POSITIVE LOGITS
     now
    0.13
     finally
    0.09
     ìĿ´ìłľ
    0.09
     ÑĤепеÑĢÑĮ
    0.09
    now
    0.09
     resume
    0.09
     NOW
    0.09
     Now
    0.09
     artık
    0.08
    finally
    0.08
    Activations Density 0.057%

    No Known Activations