© 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. 31202
    Prev
    Next
    INDEX
    Explanations

    aspects related to industry and economic activity

    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
     Synd
    -0.07
    annya
    -0.06
    ictim
    -0.06
    vae
    -0.06
    dek
    -0.06
    ertz
    -0.06
     odom
    -0.06
    ibe
    -0.06
     PLUGIN
    -0.06
    ãģ¹ãģį
    -0.06
    POSITIVE LOGITS
     headquarters
    0.11
     HQ
    0.09
     Presence
    0.08
     presence
    0.08
    Presence
    0.08
     Headquarters
    0.08
    presence
    0.08
     campus
    0.07
    ειο
    0.07
     town
    0.07
    Activations Density 0.027%

    No Known Activations