© 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. 22-LLAMASCOPE-RES-131K
    11. 3645
    Prev
    Next
    INDEX
    Explanations

    references to time periods and cultural contexts

    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
    inant
    -0.07
    âĺĨ
    -0.07
    cgi
    -0.07
    inand
    -0.06
    irler
    -0.06
    EK
    -0.06
    Associated
    -0.06
     Giles
    -0.06
    ugins
    -0.06
    rieb
    -0.06
    POSITIVE LOGITS
     Stone
    0.07
    ught
    0.07
     stone
    0.07
     suy
    0.07
    Stone
    0.07
     late
    0.07
     dot
    0.06
     past
    0.06
    éķ
    0.06
    utow
    0.06
    Activations Density 0.021%

    No Known Activations