© 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. 1169
    Prev
    Next
    INDEX
    Explanations

    geographical and environmental references

    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
     Harbour
    -0.07
     Harbor
    -0.07
    î
    -0.06
    ammers
    -0.06
     Casc
    -0.06
     segregated
    -0.06
    248
    -0.06
    Broad
    -0.06
     bidi
    -0.06
    гоÑĢод
    -0.06
    POSITIVE LOGITS
     within
    0.09
     bis
    0.08
    Within
    0.07
     Within
    0.07
     near
    0.07
     border
    0.07
     dentro
    0.07
    within
    0.07
     land
    0.07
    è·¨
    0.07
    Activations Density 0.057%

    No Known Activations