© 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. 96032
    Prev
    Next
    INDEX
    Explanations

    sentences that describe states of being, likelihoods, or past occurrences

    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
    elmet
    -0.07
    lyn
    -0.06
    mont
    -0.06
    vd
    -0.06
    qs
    -0.06
     Clement
    -0.06
     Recent
    -0.05
    è¿İ
    -0.05
    éĤ£ç§į
    -0.05
    çı
    -0.05
    POSITIVE LOGITS
     happening
    0.07
    838
    0.07
    abies
    0.07
    견
    0.07
    811
    0.06
    ТÐŀ
    0.06
    chema
    0.06
    alles
    0.06
     Å¡t
    0.06
    steder
    0.06
    Activations Density 0.008%

    No Known Activations