© 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. 129956
    Prev
    Next
    INDEX
    Explanations

    proper nouns and location names

    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
    ripe
    -0.08
    utex
    -0.07
    icut
    -0.07
    callable
    -0.07
    IELD
    -0.06
    bette
    -0.06
    oÄŁlu
    -0.06
    OrNil
    -0.06
    isz
    -0.06
    archs
    -0.06
    POSITIVE LOGITS
     news
    0.07
     Pulse
    0.07
    Times
    0.06
    -related
    0.06
     Times
    0.06
     TIMES
    0.06
    -focused
    0.06
    -centric
    0.06
     times
    0.06
     bü
    0.06
    Activations Density 0.029%

    No Known Activations