© 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. 39733
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional expertise and safely completing tasks

    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
    526
    -0.06
    .sc
    -0.06
    421
    -0.06
     unb
    -0.06
    igy
    -0.06
    (=
    -0.06
    667
    -0.06
     Kumar
    -0.05
    igne
    -0.05
    ุà¹ī
    -0.05
    POSITIVE LOGITS
    nbsp
    0.07
    allest
    0.07
    atures
    0.07
    AttributeValue
    0.07
    ishops
    0.06
    elerik
    0.06
    loo
    0.06
    peria
    0.06
     '}
    0.06
    urch
    0.06
    Activations Density 0.002%

    No Known Activations