© 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. 72563
    Prev
    Next
    INDEX
    Explanations

    key roles and functions of information technology in academic settings

    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
     Swiss
    -0.06
    ROL
    -0.06
     len
    -0.05
     do
    -0.05
     j
    -0.05
     Voc
    -0.05
    pane
    -0.05
     Walters
    -0.05
    abus
    -0.05
    ACA
    -0.05
    POSITIVE LOGITS
    /umd
    0.09
    @email
    0.09
     Regents
    0.09
     University
    0.08
     chancellor
    0.08
    University
    0.08
    ancellor
    0.08
     UNIVERSITY
    0.08
     ün
    0.08
    _um
    0.07
    Activations Density 0.100%

    No Known Activations