© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 1326
    Prev
    Next
    INDEX
    Explanations

    references to scientific research and advancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Technical language from scientific literature focusing on diagnostic methods, laboratory techniques, and research procedures, often in medical or biological contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    exe
    -0.07
     plá
    -0.07
    اعات
    -0.07
    agenta
    -0.06
    isson
    -0.06
    acon
    -0.06
     accounted
    -0.06
    .AppendFormat
    -0.06
    ynes
    -0.06
    psy
    -0.06
    POSITIVE LOGITS
    Detect
    0.08
     detection
    0.08
     false
    0.08
     discrim
    0.08
     detecting
    0.07
    false
    0.07
     discrimination
    0.07
     Discrim
    0.07
     Detect
    0.07
     detective
    0.07
    Activations Density 0.156%

    No Known Activations