© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 54637
    Prev
    Next
    INDEX
    Explanations

    references to educational and gender-related topics, alongside geographical and political elements

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    OMP
    -0.07
     indeed
    -0.07
    ãģĿãģĹãģ¦
    -0.06
    ombat
    -0.06
    issen
    -0.06
    orget
    -0.06
    они
    -0.06
    oblin
    -0.06
     ëĺIJëĬĶ
    -0.06
    inue
    -0.06
    POSITIVE LOGITS
     ones
    0.11
     counterpart
    0.11
     counterparts
    0.10
     similarly
    0.09
     version
    0.09
     equivalent
    0.08
     Ones
    0.08
    version
    0.08
     equivalents
    0.08
    -version
    0.08
    Activations Density 0.058%

    No Known Activations