© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14125
    Prev
    Next
    INDEX
    Explanations

    terms related to visibility and presence

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    isle
    -0.08
    spi
    -0.07
    rena
    -0.07
    ripp
    -0.07
    kr
    -0.07
    illard
    -0.07
    cs
    -0.07
     solidity
    -0.07
    zon
    -0.07
    uro
    -0.07
    POSITIVE LOGITS
    ock
    0.08
    263
    0.07
    quez
    0.06
    оÑĩ
    0.06
    ory
    0.06
    813
    0.06
    ights
    0.06
    (visible
    0.06
    itarian
    0.06
    izzard
    0.06
    Activations Density 0.008%

    No Known Activations