© 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. 31530
    Prev
    Next
    INDEX
    Explanations

    references to significant events or societal issues

    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
     tonight
    -0.10
     yesterday
    -0.10
     tomorrow
    -0.09
     Yesterday
    -0.09
     today
    -0.09
    Yesterday
    -0.08
    æĺ¨
    -0.08
     Tonight
    -0.08
    Tonight
    -0.07
    today
    -0.07
    POSITIVE LOGITS
    ãģķãģ¾
    0.08
    202
    0.08
    enet
    0.07
     ephem
    0.07
    ảo
    0.07
    igi
    0.06
     Kaynak
    0.06
    Û²Û°Û²
    0.06
    antee
    0.06
    iag
    0.06
    Activations Density 0.000%

    No Known Activations