© 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. 5-LLAMASCOPE-RES-131K
    6. 126840
    Prev
    Next
    INDEX
    Explanations

    mentions of locations and settings within narratives

    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
    okt
    -0.07
    headed
    -0.06
    isse
    -0.06
     огÑĢа
    -0.06
    átis
    -0.06
     apt
    -0.06
    chn
    -0.06
     èı²å¾ĭ宾
    -0.06
    otas
    -0.06
    .lambda
    -0.06
    POSITIVE LOGITS
    hart
    0.07
    ConverterFactory
    0.06
    IA
    0.06
    ald
    0.06
    aterangepicker
    0.06
    Stuff
    0.06
    hone
    0.06
    IV
    0.06
     Trick
    0.06
     trailing
    0.06
    Activations Density 0.010%

    No Known Activations