© 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. 108719
    Prev
    Next
    INDEX
    Explanations

    financial statistics and commitments related to community and infrastructure projects

    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
    uraa
    -0.07
    .scalablytyped
    -0.07
    quo
    -0.06
    phem
    -0.06
    esh
    -0.06
     contemporary
    -0.06
    acho
    -0.06
    gli
    -0.06
    quila
    -0.06
    arrant
    -0.06
    POSITIVE LOGITS
     already
    0.16
    already
    0.15
     Already
    0.14
    Already
    0.14
    å·²ç»ı
    0.12
    å·²
    0.12
    _already
    0.11
     å·²
    0.10
     sudah
    0.10
    _ALREADY
    0.10
    Activations Density 0.024%

    No Known Activations