© 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 EvalsExportsinterp-engineNEWAPI 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. 92092
    Prev
    Next
    INDEX
    Explanations

    terms related to actions, particularly in technical or procedural contexts

    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
    ÅĦ
    -0.08
    олож
    -0.08
    аÑĢÑı
    -0.07
    ___↵↵
    -0.07
    luk
    -0.07
     darm
    -0.07
    ÅĻiv
    -0.07
     plá
    -0.07
    yp
    -0.07
    ammen
    -0.07
    POSITIVE LOGITS
     to
    0.21
    _to
    0.12
    	to
    0.10
    åĪ°
    0.10
    to
    0.10
    åĪ°çļĦ
    0.10
     Ø¥ÙĦÙī
    0.10
    -to
    0.10
     tp
    0.09
     toItem
    0.09
    Activations Density 0.093%

    No Known Activations