© 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. 55694
    Prev
    Next
    INDEX
    Explanations

    words indicating comprehension or clarity

    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
    alli
    -0.08
    omial
    -0.07
    ature
    -0.07
    acea
    -0.07
    azon
    -0.07
     Laur
    -0.07
    itals
    -0.06
    zw
    -0.06
    ponder
    -0.06
    ergic
    -0.06
    POSITIVE LOGITS
    REAK
    0.07
    932
    0.06
     Fav
    0.06
    âĨĵ
    0.06
    wis
    0.06
     democr
    0.06
     Jude
    0.06
     ash
    0.06
    lém
    0.06
    âĶĤ
    0.06
    Activations Density 0.012%

    No Known Activations