© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 86910
    Prev
    Next
    INDEX
    Explanations

    conjunctions and their associated phrases relating to contrast or comparison

    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
    ninger
    -0.06
    Å¡i
    -0.06
    utz
    -0.06
     pij
    -0.06
    ез
    -0.06
    olin
    -0.06
    itably
    -0.06
     Vo
    -0.06
    essler
    -0.06
    ÑĮÑİ
    -0.06
    POSITIVE LOGITS
     less
    0.09
     naopak
    0.07
    _LESS
    0.07
     but
    0.07
    lessness
    0.07
     convers
    0.07
     LESS
    0.07
     fused
    0.07
     moins
    0.07
     Less
    0.07
    Activations Density 0.067%

    No Known Activations