© 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. 9-LLAMASCOPE-RES-131K
    11. 95338
    Prev
    Next
    INDEX
    Explanations

    counts of replies and interactions in discussions

    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
    alsy
    -0.08
    indow
    -0.08
    atri
    -0.07
    ickt
    -0.07
    antha
    -0.07
    avic
    -0.07
    raquo
    -0.07
    EventArgs
    -0.07
     Debt
    -0.07
    chyb
    -0.07
    POSITIVE LOGITS
    ripper
    0.06
     Marks
    0.06
     idle
    0.05
    νÏĮ
    0.05
     Kerry
    0.05
     starter
    0.05
    SetActive
    0.05
     Hi
    0.05
     consec
    0.05
     roi
    0.05
    Activations Density 0.001%

    No Known Activations