© 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 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. 106171
    Prev
    Next
    INDEX
    Explanations

    references to statistics or reports regarding data and internet usage in India

    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
    igon
    -0.06
    enic
    -0.06
    emann
    -0.06
     plat
    -0.06
     Brill
    -0.06
     Mozart
    -0.06
     per
    -0.06
    adier
    -0.06
    blr
    -0.06
    aupt
    -0.06
    POSITIVE LOGITS
    ORITY
    0.07
    èĦ±
    0.07
    mada
    0.07
    ocs
    0.07
     Princip
    0.07
    OrNil
    0.07
    umas
    0.07
    ÙĪÙĬس
    0.07
    loff
    0.06
     scar
    0.06
    Activations Density 0.003%

    No Known Activations