© 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. 5-LLAMASCOPE-RES-131K
    11. 126727
    Prev
    Next
    INDEX
    Explanations

    numeric values and syntax relevant to programming or coding structures

    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
    nm
    -0.07
    879
    -0.07
    åĤ¬
    -0.06
    OrDefault
    -0.06
    ocz
    -0.06
    878
    -0.06
    vanished
    -0.06
    å¼ķãģį
    -0.06
    548
    -0.06
    gin
    -0.05
    POSITIVE LOGITS
    oya
    0.07
    ánh
    0.07
    anel
    0.07
    дон
    0.07
    erra
    0.06
    odyn
    0.06
     Pall
    0.06
     apparatus
    0.06
     /*#__
    0.06
     Lux
    0.06
    Activations Density 0.003%

    No Known Activations