© 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. 89678
    Prev
    Next
    INDEX
    Explanations

    collaborative language emphasizing collective action and teamwork

    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
    åĪ«
    -0.07
     ÑģмоÑĤ
    -0.07
    麻
    -0.07
    erli
    -0.07
    969
    -0.07
    aille
    -0.07
    oret
    -0.07
    folios
    -0.07
     Status
    -0.06
     Bout
    -0.06
    POSITIVE LOGITS
     together
    0.09
     Together
    0.09
    Together
    0.08
    pton
    0.07
    FORCE
    0.06
     zusammen
    0.06
     form
    0.06
     create
    0.06
     forming
    0.06
     creates
    0.06
    Activations Density 0.009%

    No Known Activations