© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 28038
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks and ellipses

    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
    ells
    -0.08
    iro
    -0.06
    ansi
    -0.06
     FactoryBot
    -0.06
    334
    -0.06
    disposing
    -0.06
     Philosoph
    -0.06
    ë°
    -0.06
    {}{↵
    -0.06
     root
    -0.06
    POSITIVE LOGITS
    itivity
    0.08
    æĬµ
    0.06
    orst
    0.06
    zing
    0.06
     æ¢
    0.06
    gest
    0.06
    mada
    0.06
    ÑıÑĩ
    0.06
    /dc
    0.06
    CAF
    0.06
    Activations Density 0.001%

    No Known Activations