© 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. 128211
    Prev
    Next
    INDEX
    Explanations

    numerical values and related terms in a technical or programming 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
    imli
    -0.07
    immel
    -0.07
    ernes
    -0.06
    TabIndex
    -0.06
    issing
    -0.06
    peri
    -0.06
    ürn
    -0.06
     Visible
    -0.06
    imes
    -0.06
     fort
    -0.06
    POSITIVE LOGITS
    -size
    0.08
    size
    0.07
    _size
    0.07
    -sized
    0.07
    102
    0.07
    	sizeof
    0.07
     sized
    0.07
    ç£
    0.07
    pipe
    0.06
     size
    0.06
    Activations Density 0.012%

    No Known Activations