© 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. 42577
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "as" in various contexts, often highlighting comparisons or conditions

    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
    ardy
    -0.07
     Garn
    -0.07
    au
    -0.07
    ourg
    -0.06
     nil
    -0.06
     ultimately
    -0.06
    ult
    -0.06
    oise
    -0.06
    oret
    -0.06
     eventual
    -0.06
    POSITIVE LOGITS
    DEX
    0.08
     slightest
    0.07
    hit
    0.07
    aneously
    0.07
     hit
    0.07
     itibaren
    0.07
     BEGIN
    0.07
     mention
    0.07
    imitives
    0.07
     begun
    0.07
    Activations Density 0.021%

    No Known Activations