© 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. 1173
    Prev
    Next
    INDEX
    Explanations

    phrases that involve actions and their consequences

    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
     irresist
    -0.07
    isÃŃ
    -0.07
    utin
    -0.07
    धर
    -0.07
    ît
    -0.06
    olith
    -0.06
    iston
    -0.06
     hva
    -0.06
    ulant
    -0.06
    úa
    -0.06
    POSITIVE LOGITS
    THEN
    0.07
    æīįèĥ½
    0.07
    then
    0.07
    anki
    0.07
     Requires
    0.07
     THEN
    0.07
     Fortunately
    0.06
    Requires
    0.06
     OTHERWISE
    0.06
    é¡»
    0.06
    Activations Density 0.045%

    No Known Activations