© 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. 26946
    Prev
    Next
    INDEX
    Explanations

    actions related to user account management and interactions

    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
    为äºĨ
    -0.09
     Äijá»ĥ
    -0.09
     aby
    -0.07
     Ñīоб
    -0.07
     ÑĩÑĤобÑĭ
    -0.07
    ÑģÑĤин
    -0.07
     длÑı
    -0.07
    еле
    -0.07
     pentru
    -0.06
    Äįit
    -0.06
    POSITIVE LOGITS
     directly
    0.08
    appropriate
    0.08
     entsprech
    0.07
     appropriate
    0.07
    Simply
    0.06
    ãģĹãĤĩãģĨ
    0.06
     Simply
    0.06
    468
    0.06
    ìĹ°
    0.06
    udi
    0.06
    Activations Density 0.060%

    No Known Activations