© 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. 15-LLAMASCOPE-RES-131K
    11. 87677
    Prev
    Next
    INDEX
    Explanations

    key concepts and terminology related to philosophical discussions and societal critiques

    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
    amet
    -0.06
    yo
    -0.06
     linear
    -0.06
    Ãłng
    -0.06
    ernet
    -0.06
    iro
    -0.06
    lamaz
    -0.06
    DEX
    -0.05
    ühr
    -0.05
    itution
    -0.05
    POSITIVE LOGITS
    Tube
    0.08
    ozilla
    0.07
     avantaj
    0.07
    æį®
    0.07
     poru
    0.07
    è«
    0.07
    íĤ¹
    0.07
    acak
    0.07
    .xhtml
    0.07
    xFFFFFF
    0.07
    Activations Density 0.000%

    No Known Activations