© 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. 17-LLAMASCOPE-RES-131K
    11. 16425
    Prev
    Next
    INDEX
    Explanations

    terms related to franchising processes and consultations

    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
    ondon
    -0.09
     íĹ
    -0.08
    женÑĮ
    -0.08
    огод
    -0.08
    úsqueda
    -0.07
    vod
    -0.07
    mÃŃt
    -0.07
    paged
    -0.07
    strap
    -0.07
    inen
    -0.07
    POSITIVE LOGITS
     pre
    0.08
     ACE
    0.06
     /
    0.06
     Denied
    0.06
     Gos
    0.06
     parallel
    0.05
     (
    0.05
     o
    0.05
     log
    0.05
     agent
    0.05
    Activations Density 0.002%

    No Known Activations