© 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. 89778
    Prev
    Next
    INDEX
    Explanations

    references to governmental or legal actions and public concerns

    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
    >manual
    -0.07
     simply
    -0.06
     kimse
    -0.06
    solete
    -0.06
     olmayan
    -0.06
    /cpp
    -0.06
    é¨
    -0.06
    ÙĬدة
    -0.06
    _Renderer
    -0.06
     requisite
    -0.06
    POSITIVE LOGITS
     potentially
    0.26
     possibly
    0.23
     potential
    0.21
     possible
    0.19
    possibly
    0.19
    åı¯èĥ½
    0.18
     possibility
    0.18
     may
    0.17
     Potential
    0.17
     Possibly
    0.17
    Activations Density 0.083%

    No Known Activations