© 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. 89500
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals with formal titles or positions

    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
    ãĥ¬ãĥ¼
    -0.07
    oller
    -0.07
    entes
    -0.07
    jt
    -0.07
    ìĨ
    -0.06
    AsStream
    -0.06
    rike
    -0.06
    istol
    -0.06
    Opens
    -0.06
    mare
    -0.06
    POSITIVE LOGITS
    acus
    0.07
    orning
    0.06
    .exc
    0.06
    ifa
    0.06
    kaz
    0.06
     clo
    0.06
     depot
    0.06
     guard
    0.06
     AAA
    0.06
    wise
    0.06
    Activations Density 0.005%

    No Known Activations