© 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. 18700
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time transitions or continuations

    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
    scribe
    -0.08
    PLETED
    -0.07
    imei
    -0.07
    omat
    -0.07
    indy
    -0.06
    probante
    -0.06
    insky
    -0.06
    odore
    -0.06
    iedade
    -0.06
    zem
    -0.06
    POSITIVE LOGITS
     recently
    0.07
    ician
    0.06
    ary
    0.06
     Gle
    0.06
    bury
    0.06
     lately
    0.06
    ãĥ»ãĥ»ãĥ»↵↵
    0.06
     candidacy
    0.06
     cli
    0.06
     Trib
    0.06
    Activations Density 0.008%

    No Known Activations