© 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. 104193
    Prev
    Next
    INDEX
    Explanations

    references to music albums and band experiences

    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
     XK
    -0.07
    NetMessage
    -0.07
    appe
    -0.07
    ØŃØ«
    -0.07
    logan
    -0.07
    ROUT
    -0.07
    VICE
    -0.07
    terror
    -0.07
    keh
    -0.07
    RGBA
    -0.07
    POSITIVE LOGITS
     exit
    0.08
     leaving
    0.07
     sever
    0.07
     was
    0.07
     ac
    0.06
     circumstances
    0.06
    exit
    0.06
     toxicity
    0.06
    è¾ŀ
    0.06
     abrupt
    0.06
    Activations Density 0.028%

    No Known Activations