© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 105319
    Prev
    Next
    INDEX
    Explanations

    phrases indicating transformation or improvement

    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
     огÑĢа
    -0.08
    inder
    -0.08
    اصÙĦ
    -0.07
    nio
    -0.07
    illos
    -0.07
    âm
    -0.07
    ľĺ
    -0.07
    kv
    -0.07
    umbn
    -0.07
     dÄ±ÅŁÄ±nda
    -0.07
    POSITIVE LOGITS
    ãĤĪãģĨ
    0.06
     Soon
    0.06
    ippi
    0.06
     perception
    0.06
    vrier
    0.06
     corrective
    0.06
     overs
    0.06
    ew
    0.06
     pans
    0.06
    ippers
    0.05
    Activations Density 0.010%

    No Known Activations