© 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. 38666
    Prev
    Next
    INDEX
    Explanations

    terms related to tyranny and authoritarianism

    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
    llib
    -0.09
    ampp
    -0.09
    ntax
    -0.07
    ãĥĭãĤ¢
    -0.07
    NCY
    -0.07
     Kil
    -0.07
    rush
    -0.07
    enso
    -0.07
    ileged
    -0.07
    ortho
    -0.07
    POSITIVE LOGITS
     Ces
    0.07
     Mach
    0.07
     Renaissance
    0.07
     advises
    0.06
     Stability
    0.06
     serv
    0.06
     instability
    0.06
     military
    0.06
    éĤ¦
    0.06
     Sesso
    0.06
    Activations Density 0.001%

    No Known Activations