© 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. 9-LLAMASCOPE-RES-131K
    11. 98257
    Prev
    Next
    INDEX
    Explanations

    references to nostalgic 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
    Å¡il
    -0.07
    lacak
    -0.07
    iyim
    -0.06
    HeaderCode
    -0.06
    bjerg
    -0.06
    isko
    -0.06
    outil
    -0.06
    hausen
    -0.06
    orrow
    -0.06
    rss
    -0.06
    POSITIVE LOGITS
    WAIT
    0.07
    PU
    0.06
    onom
    0.06
     Thumb
    0.06
     mold
    0.06
    ãĥ¼ãĥł
    0.06
    ubes
    0.06
     Ment
    0.06
     Campo
    0.06
    asan
    0.06
    Activations Density 0.001%

    No Known Activations