© 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. 15-LLAMASCOPE-RES-131K
    11. 86080
    Prev
    Next
    INDEX
    Explanations

    terms related to brand names and their manufacturers

    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
    asaki
    -0.07
    tain
    -0.07
    ene
    -0.06
    onda
    -0.06
    apy
    -0.06
    esser
    -0.06
    atto
    -0.06
    ģµ
    -0.06
    edo
    -0.06
    ickey
    -0.06
    POSITIVE LOGITS
    caff
    0.08
    -name
    0.08
    .blur
    0.07
    .ReadFile
    0.07
    ernes
    0.07
    ouver
    0.07
    iveau
    0.07
    íĺij
    0.07
    .navigator
    0.07
    ãĤ
    0.06
    Activations Density 0.013%

    No Known Activations