© 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 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. 15-LLAMASCOPE-RES-131K
    11. 87902
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and bureaucratic processes

    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
    ansom
    -0.06
    andon
    -0.06
    peg
    -0.06
    omu
    -0.06
    pa
    -0.06
    ÑĤеÑħ
    -0.06
     Rodgers
    -0.06
     dot
    -0.06
     peg
    -0.06
    body
    -0.06
    POSITIVE LOGITS
    izzo
    0.08
    701
    0.08
    cea
    0.07
    quia
    0.07
    ibri
    0.07
    enty
    0.07
    successfully
    0.07
    #af
    0.07
    utow
    0.07
    ¤
    0.07
    Activations Density 0.027%

    No Known Activations