© 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. 80767
    Prev
    Next
    INDEX
    Explanations

    conjunctions and logical operators indicating relationships between concepts

    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
    verity
    -0.07
    .Selenium
    -0.07
    ethoven
    -0.06
    ONGL
    -0.06
    _DECLARE
    -0.06
    олÑı
    -0.06
    avers
    -0.06
    okie
    -0.06
    à¸Ļà¸Ķ
    -0.06
    OKIE
    -0.06
    POSITIVE LOGITS
     Fraction
    0.08
     иÑģ
    0.07
     Slut
    0.07
    ipl
    0.07
    replacement
    0.07
    ango
    0.07
     Services
    0.06
    WidgetItem
    0.06
     clo
    0.06
    æı
    0.06
    Activations Density 0.000%

    No Known Activations