© 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. 117057
    Prev
    Next
    INDEX
    Explanations

    references to sustainable development and environmental goals

    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
    enthal
    -0.08
    neau
    -0.06
    á»ħ
    -0.06
     overl
    -0.06
     çģ
    -0.06
    instein
    -0.06
     inert
    -0.06
    za
    -0.06
     Showcase
    -0.05
    cri
    -0.05
    POSITIVE LOGITS
     goals
    0.12
     Goals
    0.12
     objectives
    0.10
    goals
    0.10
    203
    0.10
     Goal
    0.10
    Goals
    0.09
     SD
    0.09
     goal
    0.09
    Goal
    0.08
    Activations Density 0.152%

    No Known Activations