© 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. 56555
    Prev
    Next
    INDEX
    Explanations

    words that exhibit high levels of activity or intensity

    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
    faces
    -0.06
    mpar
    -0.06
    bench
    -0.06
    اÙĩÙħ
    -0.06
    achen
    -0.06
    isy
    -0.06
    uga
    -0.06
    év
    -0.06
    unker
    -0.06
    ysa
    -0.06
    POSITIVE LOGITS
    aleur
    0.06
     peri
    0.06
    áno
    0.06
     Kostenlos
    0.06
     vat
    0.06
    umeric
    0.06
    ίν
    0.06
    ³
    0.06
    odos
    0.06
    CELER
    0.06
    Activations Density 0.060%

    No Known Activations