© 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. 5665
    Prev
    Next
    INDEX
    Explanations

    mentions of notable individuals and their associated accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    leta
    -0.08
    danger
    -0.08
    parm
    -0.07
    ietf
    -0.07
     yıldır
    -0.07
    powers
    -0.07
     current
    -0.07
    essler
    -0.07
     fav
    -0.06
     Addr
    -0.06
    POSITIVE LOGITS
     died
    0.08
    192
    0.07
     dying
    0.07
     die
    0.07
    ighthouse
    0.06
     Cay
    0.06
     Secret
    0.06
     Die
    0.06
     succ
    0.06
    iral
    0.06
    Activations Density 0.006%

    No Known Activations