© 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. 31745
    Prev
    Next
    INDEX
    Explanations

    references to collective action and initiatives aimed at social betterment

    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
    itel
    -0.07
    berger
    -0.07
    quirer
    -0.07
    htub
    -0.07
     sag
    -0.07
    ersen
    -0.06
    Ħĸ
    -0.06
    BT
    -0.06
    apot
    -0.06
    ris
    -0.06
    POSITIVE LOGITS
     editorial
    0.07
     Editorial
    0.06
     relev
    0.06
     platform
    0.06
     our
    0.06
    ortho
    0.06
     Distribution
    0.06
     distribution
    0.06
    istribution
    0.05
     Sphinx
    0.05
    Activations Density 0.003%

    No Known Activations