© 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. 15-LLAMASCOPE-RES-131K
    11. 27442
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specific relationships or qualities among multiple subjects

    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
    etine
    -0.06
     meas
    -0.06
    liest
    -0.06
    ÏĥÏĦη
    -0.06
    anlık
    -0.06
    UTO
    -0.06
    axy
    -0.06
     poil
    -0.06
    ao
    -0.06
    metric
    -0.06
    POSITIVE LOGITS
     sorts
    0.09
     sort
    0.08
     magnitude
    0.07
    adow
    0.07
    rok
    0.06
    ör
    0.06
     Joyce
    0.06
    sort
    0.06
     extent
    0.06
    Ïģκ
    0.06
    Activations Density 0.108%

    No Known Activations