© 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. 9-LLAMASCOPE-RES-131K
    11. 96242
    Prev
    Next
    INDEX
    Explanations

    references to technology and hardware products

    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
     éĸ¢
    -0.06
    avir
    -0.06
    acades
    -0.06
    ONO
    -0.06
    bere
    -0.06
    buah
    -0.06
    Ī¬
    -0.06
    eam
    -0.06
    icari
    -0.06
    Å
    -0.06
    POSITIVE LOGITS
    EEP
    0.06
    _excerpt
    0.06
     Variant
    0.06
     Noah
    0.06
     variants
    0.06
     thay
    0.06
    ÙĦØ©
    0.06
    anou
    0.06
    phy
    0.06
    ajo
    0.06
    Activations Density 0.017%

    No Known Activations