© 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. 91684
    Prev
    Next
    INDEX
    Explanations

    instances of the word "with" used in various contexts

    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
     instanceof
    -0.07
    ÃŃsto
    -0.07
    سط
    -0.07
     )↵↵↵↵↵↵↵↵
    -0.07
    eec
    -0.07
     برخ
    -0.07
    mÃŃ
    -0.06
     sami
    -0.06
     crossorigin
    -0.06
    extr
    -0.06
    POSITIVE LOGITS
    ichten
    0.08
     regard
    0.08
     no
    0.07
     being
    0.07
     only
    0.07
     exception
    0.06
     regards
    0.06
    chten
    0.06
    coli
    0.06
    zap
    0.06
    Activations Density 0.041%

    No Known Activations