© 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. 9-LLAMASCOPE-RES-131K
    11. 99223
    Prev
    Next
    INDEX
    Explanations

    references to high-quality services or products

    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
    sse
    -0.06
    379
    -0.06
    ategorized
    -0.06
     пÑĥ
    -0.06
    chu
    -0.06
    ignKey
    -0.06
     Reading
    -0.06
    272
    -0.06
    nic
    -0.06
    :
    -0.06
    POSITIVE LOGITS
     quality
    0.09
    ACHE
    0.08
    -quality
    0.07
    ç´¹
    0.07
    ache
    0.07
    assage
    0.07
    è´¨éĩı
    0.07
     pathMatch
    0.07
    	throws
    0.07
    Quality
    0.07
    Activations Density 0.011%

    No Known Activations