© 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. 127862
    Prev
    Next
    INDEX
    Explanations

    references to off-topic discussions and financial terms related to accounting and invoicing

    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
    plex
    -0.08
     xuyên
    -0.08
    üz
    -0.07
     Dün
    -0.07
    chants
    -0.07
    ÑĦек
    -0.07
    odd
    -0.07
    cury
    -0.07
    onya
    -0.07
    -hearted
    -0.07
    POSITIVE LOGITS
    /on
    0.13
    /out
    0.11
    /off
    0.11
    /down
    0.09
    /at
    0.07
    edly
    0.07
    /in
    0.06
    -bound
    0.06
    /from
    0.06
    (Un
    0.06
    Activations Density 0.024%

    No Known Activations