© 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. 116364
    Prev
    Next
    INDEX
    Explanations

    the concept of pairs or dualities

    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
    OUCH
    -0.07
    ouch
    -0.07
    proof
    -0.06
    ÂŃing
    -0.06
    /Instruction
    -0.06
    Ñģм
    -0.06
    ائز
    -0.06
    DAC
    -0.06
    beb
    -0.06
    ÑĢо
    -0.06
    POSITIVE LOGITS
     dozen
    0.09
    /all
    0.08
     depending
    0.08
     thousand
    0.07
     Hundred
    0.07
    ero
    0.07
    ieme
    0.07
    entieth
    0.07
    elp
    0.07
    eldo
    0.07
    Activations Density 0.003%

    No Known Activations