© 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. 123249
    Prev
    Next
    INDEX
    Explanations

    references to policies and legislation

    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
    ooter
    -0.07
    rana
    -0.07
    rne
    -0.07
    inc
    -0.07
    Porno
    -0.06
    )frame
    -0.06
    å²
    -0.06
    ysa
    -0.06
    dera
    -0.06
    ÇIJ
    -0.06
    POSITIVE LOGITS
     altogether
    0.08
     because
    0.08
     partly
    0.07
     tooth
    0.07
     being
    0.07
    being
    0.07
     vì
    0.06
    aying
    0.06
    isko
    0.06
     principle
    0.06
    Activations Density 0.032%

    No Known Activations