© 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. 9-LLAMASCOPE-RES-131K
    11. 98223
    Prev
    Next
    INDEX
    Explanations

    instances of comparisons and contrasts within texts

    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
    ÅĻet
    -0.08
     @@↵
    -0.08
    á»iji
    -0.08
     åIJįåīį
    -0.08
    éŀ
    -0.08
    릿
    -0.07
    geber
    -0.07
    ì§ĢìĽIJ
    -0.07
    okud
    -0.07
    DIRECT
    -0.07
    POSITIVE LOGITS
    0.08
     whereas
    0.06
    a
    0.06
    1
    0.06
     reaction
    0.05
    ock
    0.05
    weak
    0.05
     twin
    0.05
    omin
    0.05
    by
    0.05
    Activations Density 0.083%

    No Known Activations