© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106554
    Prev
    Next
    INDEX
    Explanations

    phrases related to modification and adjustment

    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
    	Copyright
    -0.09
    _exports
    -0.07
    ilir
    -0.07
    finity
    -0.07
    jam
    -0.07
    lider
    -0.07
    Å¡t
    -0.06
    DOT
    -0.06
    rases
    -0.06
    urger
    -0.06
    POSITIVE LOGITS
     remove
    0.10
     subtract
    0.09
     removal
    0.09
    remove
    0.09
     removed
    0.09
     removes
    0.08
     removing
    0.08
    -remove
    0.08
     Removes
    0.08
     change
    0.07
    Activations Density 0.012%

    No Known Activations