© 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. 9-LLAMASCOPE-RES-131K
    11. 99086
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating measurement or evaluation

    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
    endra
    -0.06
    astr
    -0.06
    ÃŃna
    -0.06
    ayi
    -0.06
    į°
    -0.06
    omanip
    -0.06
    аÑĤоÑĢ
    -0.06
    unos
    -0.06
    amins
    -0.06
    ropoda
    -0.06
    POSITIVE LOGITS
     trib
    0.08
    loy
    0.07
    åĶĩ
    0.07
    -transitional
    0.07
    물ìĿĦ
    0.06
    rew
    0.06
    EDI
    0.06
    /month
    0.06
     provid
    0.06
    ầu
    0.06
    Activations Density 0.000%

    No Known Activations