© 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. 116626
    Prev
    Next
    INDEX
    Explanations

    words related to botanical or plant classification

    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
     McCart
    -0.08
    itchen
    -0.07
    .share
    -0.07
    æ¹¾
    -0.07
    縮
    -0.07
    _PCI
    -0.07
    çĶ³
    -0.06
    als
    -0.06
    åĩ¡
    -0.06
     Seam
    -0.06
    POSITIVE LOGITS
    ITO
    0.06
    oriously
    0.06
     webs
    0.06
    iesen
    0.06
    Ĥæķ°
    0.06
    markup
    0.06
     Äĥn
    0.06
    orz
    0.06
    ů
    0.06
     Oswald
    0.06
    Activations Density 0.001%

    No Known Activations