© 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. 105811
    Prev
    Next
    INDEX
    Explanations

    words related to speed or pace

    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
    sip
    -0.09
    ignum
    -0.08
    s
    -0.07
    nul
    -0.07
    Ùĩ
    -0.07
    ses
    -0.07
    .metro
    -0.07
    sav
    -0.07
    unker
    -0.07
    emean
    -0.07
    POSITIVE LOGITS
     fast
    0.07
    671
    0.07
    sequently
    0.06
    /fast
    0.06
     jumps
    0.06
     Fast
    0.06
    yr
    0.06
    ley
    0.06
    fast
    0.06
    ziej
    0.06
    Activations Density 0.002%

    No Known Activations