© 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. 63217
    Prev
    Next
    INDEX
    Explanations

    reporting and discussions on environmental and public health 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
     sans
    -0.06
    202
    -0.06
     gradually
    -0.06
    iff
    -0.06
     eventually
    -0.05
     Fowler
    -0.05
     somebody
    -0.05
    chief
    -0.05
     isn
    -0.05
     Sundays
    -0.05
    POSITIVE LOGITS
     tod
    0.09
     today
    0.09
     tonight
    0.09
     PRESS
    0.09
    esin
    0.08
     завÑĤÑĢа
    0.08
     tomorrow
    0.08
    bservice
    0.08
    ropa
    0.07
    anness
    0.07
    Activations Density 0.014%

    No Known Activations