© 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. 123262
    Prev
    Next
    INDEX
    Explanations

    phrases related to governance and political events

    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
    ernaut
    -0.08
    uur
    -0.07
    ì§ĵ
    -0.07
    .oc
    -0.07
    ½
    -0.06
     prostitutas
    -0.06
    obus
    -0.06
    ivec
    -0.06
    물
    -0.06
    ìĦ±ìĿ´
    -0.06
    POSITIVE LOGITS
     absence
    0.13
     absent
    0.10
     while
    0.09
     Abs
    0.09
     without
    0.09
     abs
    0.09
    abs
    0.08
     Without
    0.08
    without
    0.08
     WITHOUT
    0.08
    Activations Density 0.070%

    No Known Activations