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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 129532
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and research organizations

    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
    .uf
    -0.07
    iegel
    -0.06
    ỳ
    -0.06
    awn
    -0.06
    oust
    -0.06
     fug
    -0.06
     Rossi
    -0.06
    lick
    -0.06
    agit
    -0.06
    dag
    -0.06
    POSITIVE LOGITS
     USA
    0.07
    obao
    0.07
    ÃŃnÄĽ
    0.07
    USA
    0.06
     usa
    0.06
    ãĥ¡ãĥªãĤ«
    0.06
    rames
    0.06
     æ¢
    0.06
    mapper
    0.06
     ElementType
    0.06
    Activations Density 0.013%

    No Known Activations