© 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 EvalsExportsinterp-engineNEWAPI 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. 79666
    Prev
    Next
    INDEX
    Explanations

    terms related to service industries and their offerings

    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
    alm
    -0.06
     muh
    -0.06
     aside
    -0.06
     Electoral
    -0.05
     FY
    -0.05
    astos
    -0.05
    enburg
    -0.05
     Dro
    -0.05
    PIO
    -0.05
    eken
    -0.05
    POSITIVE LOGITS
    اتÙĩ
    0.09
     matters
    0.08
     technology
    0.07
     awakeFromNib
    0.07
    ublish
    0.07
    atte
    0.07
    ainment
    0.07
     nad
    0.07
    igon
    0.07
    374
    0.07
    Activations Density 0.044%

    No Known Activations