© 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. 42791
    Prev
    Next
    INDEX
    Explanations

    references to death and its societal implications

    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
     oci
    -0.07
     META
    -0.07
    iddy
    -0.07
    asted
    -0.07
    eyse
    -0.07
    errated
    -0.06
    .gdx
    -0.06
    kuk
    -0.06
    áno
    -0.06
     tom
    -0.06
    POSITIVE LOGITS
    æŀ
    0.07
    ACHE
    0.06
    ene
    0.06
    åľĴ
    0.06
    CH
    0.05
     decay
    0.05
     Supporters
    0.05
     Ware
    0.05
     Sachs
    0.05
    inkel
    0.05
    Activations Density 0.003%

    No Known Activations