© 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. 95844
    Prev
    Next
    INDEX
    Explanations

    quantifiable measures or objects within a recipe or instruction context

    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
    allis
    -0.07
    asca
    -0.07
    sit
    -0.06
    ermen
    -0.06
    aepernick
    -0.06
    upe
    -0.06
     EntityState
    -0.06
    itary
    -0.06
     Immediate
    -0.06
     VIA
    -0.06
    POSITIVE LOGITS
    Ctrls
    0.07
    ìŀ¡
    0.07
    .onView
    0.07
    å¥
    0.07
    visa
    0.07
    ovÃŃ
    0.07
    ái
    0.07
     gön
    0.07
     furn
    0.06
    館
    0.06
    Activations Density 0.015%

    No Known Activations