© 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. 5903
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords or syntax

    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
     granted
    -0.06
    roid
    -0.06
    if
    -0.06
    roids
    -0.06
    rios
    -0.06
    1
    -0.06
    iff
    -0.06
     Crest
    -0.06
    is
    -0.06
    ari
    -0.06
    POSITIVE LOGITS
    大åħ¨
    0.08
    SWG
    0.07
    ledi
    0.07
    CompleteListener
    0.07
     çİ
    0.07
    Ïħνα
    0.07
    stash
    0.07
     yourselves
    0.07
    ëŀĢ
    0.07
    'gc
    0.07
    Activations Density 0.000%

    No Known Activations