© 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. 86520
    Prev
    Next
    INDEX
    Explanations

    terms related to military contracts and procurement processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Fragments of Portuguese words that occur at text split points or line breaks, showing how words are segmented when text is divided.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ención
    -0.07
     nuest
    -0.07
     Gard
    -0.06
    amiento
    -0.06
     conoc
    -0.06
     Dip
    -0.06
    iego
    -0.06
     puerto
    -0.06
    Venta
    -0.06
     mayo
    -0.06
    POSITIVE LOGITS
    ôn
    0.11
    inha
    0.10
    inho
    0.10
     Brazilian
    0.10
    idade
    0.10
     itens
    0.10
    agem
    0.10
    ão
    0.09
    êm
    0.09
     ê
    0.09
    Activations Density 0.416%

    No Known Activations