© 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. 121636
    Prev
    Next
    INDEX
    Explanations

    specific historical locations and landmarks

    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
    security
    -0.07
     Embedded
    -0.06
     security
    -0.06
     embedding
    -0.06
    Embed
    -0.06
    tha
    -0.06
     pedest
    -0.06
    ipt
    -0.06
    reation
    -0.05
    Embedded
    -0.05
    POSITIVE LOGITS
     house
    0.09
     restored
    0.08
    еÑĢап
    0.07
    ourd
    0.07
     museum
    0.07
    หล
    0.07
    ìĽĢ
    0.07
    ÑĤÑİ
    0.07
     restoration
    0.07
    oldem
    0.07
    Activations Density 0.034%

    No Known Activations