© 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. 31396
    Prev
    Next
    INDEX
    Explanations

    lines that begin with slashes, indicating comments in code

    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
    plat
    -0.07
    inar
    -0.06
    amen
    -0.06
    rolling
    -0.06
    emma
    -0.06
    ity
    -0.06
    Roll
    -0.06
     rolls
    -0.06
     seeding
    -0.06
    arry
    -0.06
    POSITIVE LOGITS
    olet
    0.07
    licated
    0.07
     Woods
    0.07
    tik
    0.07
    osate
    0.07
    ivial
    0.06
    	Copyright
    0.06
    tur
    0.06
    uhn
    0.06
    locals
    0.06
    Activations Density 0.002%

    No Known Activations