© 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. 38287
    Prev
    Next
    INDEX
    Explanations

    references to contact information and university services

    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
    itu
    -0.06
    илÑı
    -0.06
     caption
    -0.06
    eya
    -0.06
    PLUS
    -0.05
     Amend
    -0.05
    pek
    -0.05
    _subtitle
    -0.05
    requested
    -0.05
     Mey
    -0.05
    POSITIVE LOGITS
    -Cs
    0.07
    ctrine
    0.07
    ipop
    0.07
    AccessException
    0.07
    ADX
    0.06
    çĬ
    0.06
    XI
    0.06
    oria
    0.06
     escalate
    0.06
     CharSet
    0.06
    Activations Density 0.000%

    No Known Activations