© 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. 85091
    Prev
    Next
    INDEX
    Explanations

    instances of Latin-derived vocabulary commonly used in formal or academic writing

    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
    phan
    -0.07
    awi
    -0.07
    ekk
    -0.07
     reco
    -0.07
     Там
    -0.07
    ®
    -0.07
    ingly
    -0.07
    ivor
    -0.07
    aby
    -0.06
    ecast
    -0.06
    POSITIVE LOGITS
    isel
    0.06
    nul
    0.06
    radient
    0.06
    -eng
    0.05
    inati
    0.05
    .myapplication
    0.05
    589
    0.05
    ãĥĭãĥĥãĤ¯
    0.05
    StackNavigator
    0.05
    918
    0.05
    Activations Density 0.001%

    No Known Activations