© 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. 86199
    Prev
    Next
    INDEX
    Explanations

    ordinal indicators or suffixes in numerical contexts

    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
    cre
    -0.07
    -To
    -0.06
    modity
    -0.06
    alace
    -0.06
    iling
    -0.06
     Martins
    -0.06
    309
    -0.06
    iete
    -0.06
    miss
    -0.06
    rement
    -0.06
    POSITIVE LOGITS
    ichel
    0.07
    ĥĿ
    0.07
     diffusion
    0.06
    .obs
    0.06
     Hlav
    0.06
     Basket
    0.06
    strup
    0.06
    =""><
    0.06
     verst
    0.06
    diff
    0.06
    Activations Density 0.000%

    No Known Activations