© 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. 18849
    Prev
    Next
    INDEX
    Explanations

    documents and concepts related to legal agreements and formal authorizations

    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
     Fist
    -0.06
    .require
    -0.06
    (ConfigurationManager
    -0.06
    -active
    -0.05
     actively
    -0.05
     Postal
    -0.05
    _NAMESPACE
    -0.05
    اØŃÛĮ
    -0.05
     Cham
    -0.05
     recurrence
    -0.05
    POSITIVE LOGITS
     dated
    0.10
    dated
    0.08
    ocities
    0.08
     vitae
    0.08
     signed
    0.08
    igator
    0.07
    овеÑĢ
    0.07
    marshall
    0.07
     Wort
    0.07
    enant
    0.07
    Activations Density 0.033%

    No Known Activations