© 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. 14375
    Prev
    Next
    INDEX
    Explanations

    references to land management and legal actions involving land

    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
     Glo
    -0.07
    Atlanta
    -0.06
     Atlanta
    -0.06
     RVA
    -0.06
     Beach
    -0.06
    ée
    -0.06
     Westbrook
    -0.06
    quete
    -0.06
     Ä°z
    -0.05
    ansa
    -0.05
    POSITIVE LOGITS
     Interior
    0.09
     Devils
    0.08
    apache
    0.08
     Apache
    0.07
    лÑİ
    0.07
    DOI
    0.07
     Pai
    0.07
    /resource
    0.07
    keley
    0.07
    imson
    0.07
    Activations Density 0.007%

    No Known Activations