© 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. 123503
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific terminology related to physics and numerical analysis

    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
     â
    -0.07
     aforementioned
    -0.07
    -0.06
    leyen
    -0.06
     ‘
    -0.06
    984
    -0.06
     [âĢ¦]
    -0.06
    ylv
    -0.06
     theor
    -0.06
    abus
    -0.06
    POSITIVE LOGITS
    õi
    0.08
    ronics
    0.08
    istrovstvÃŃ
    0.08
    doch
    0.08
    ÑĢÑıдÑĥ
    0.08
    Æ°Æ¡i
    0.07
    å¨ĺ
    0.07
    Ỽ
    0.07
    .ai
    0.07
     {?}
    0.07
    Activations Density 0.001%

    No Known Activations