© 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. 126503
    Prev
    Next
    INDEX
    Explanations

    discussions about legislation and advocacy efforts

    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
    ãĤ¶ãĥ¼
    -0.07
    ávÄĽ
    -0.06
    ags
    -0.06
    rown
    -0.06
    ع
    -0.06
    ondo
    -0.06
    pg
    -0.06
     propName
    -0.06
    abad
    -0.06
     Boone
    -0.06
    POSITIVE LOGITS
     progress
    0.08
    obil
    0.07
     momentum
    0.07
    Calibri
    0.07
    Timing
    0.07
    ocale
    0.07
     bills
    0.06
     Whip
    0.06
     House
    0.06
    FileVersion
    0.06
    Activations Density 0.008%

    No Known Activations