© 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. 125686
    Prev
    Next
    INDEX
    Explanations

    phrases associated with measurements and quantities

    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
    overy
    -0.07
    лаÑĩ
    -0.06
    relude
    -0.06
    STAT
    -0.06
    SES
    -0.06
    uku
    -0.06
    /topics
    -0.05
    811
    -0.05
     classNames
    -0.05
     extras
    -0.05
    POSITIVE LOGITS
    agner
    0.08
    _RW
    0.08
    onz
    0.07
    λλη
    0.07
    «a
    0.07
    ModifiedDate
    0.07
    eria
    0.07
    entifier
    0.07
    ë°ĺ
    0.07
    represented
    0.06
    Activations Density 0.007%

    No Known Activations