© 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. 27798
    Prev
    Next
    INDEX
    Explanations

    discussions about triviality and dismissiveness in societal narratives

    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
    बल
    -0.07
    ware
    -0.07
    ekler
    -0.06
    .nih
    -0.06
     Rath
    -0.06
    à¥įबर
    -0.06
     Interval
    -0.06
     conserv
    -0.06
    adÄĽ
    -0.06
    _fc
    -0.06
    POSITIVE LOGITS
     harmless
    0.11
     trivial
    0.11
     minor
    0.11
     insignificant
    0.10
    ivial
    0.10
     small
    0.09
     Minor
    0.09
    å°ı
    0.08
     insign
    0.08
    minor
    0.08
    Activations Density 0.032%

    No Known Activations