© 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. 99264
    Prev
    Next
    INDEX
    Explanations

    mentions of survival and protection in the context of animal life cycles

    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
    ully
    -0.07
    å°
    -0.07
    otts
    -0.07
    uppy
    -0.06
    allee
    -0.06
    ulg
    -0.06
    vari
    -0.06
    gle
    -0.06
    Disclosure
    -0.06
    SWG
    -0.06
    POSITIVE LOGITS
     they
    0.06
     Stark
    0.06
    asty
    0.06
    欣
    0.06
    AMED
    0.06
    彦
    0.06
    анÑĮ
    0.06
    olid
    0.06
    ambio
    0.06
    ÏĦÏī
    0.06
    Activations Density 0.005%

    No Known Activations