© 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. 69017
    Prev
    Next
    INDEX
    Explanations

    references to educational structures and curricula

    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
     grads
    -0.07
    uta
    -0.07
    zin
    -0.06
    èĩªæ²»
    -0.06
     grad
    -0.06
     graduation
    -0.06
    urdy
    -0.06
    berger
    -0.06
     Rookie
    -0.06
     zip
    -0.06
    POSITIVE LOGITS
     exp
    0.09
    lobal
    0.08
    elta
    0.08
     international
    0.07
     foreigners
    0.07
     International
    0.07
    global
    0.07
     Global
    0.06
     multinational
    0.06
     Overse
    0.06
    Activations Density 0.020%

    No Known Activations