© 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. 1293
    Prev
    Next
    INDEX
    Explanations

    references to transparency and consultation in decision-making processes

    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
    ONO
    -0.07
     kov
    -0.07
    achsen
    -0.07
    nnen
    -0.06
    628
    -0.06
    lia
    -0.06
    à¹Ģà¸Ļ
    -0.06
    isi
    -0.06
    mith
    -0.06
     neutrality
    -0.06
    POSITIVE LOGITS
     without
    0.10
     secretive
    0.09
     secrecy
    0.09
    without
    0.09
     Without
    0.08
     bypass
    0.08
    Without
    0.08
     ohne
    0.07
     secret
    0.07
     WITHOUT
    0.07
    Activations Density 0.028%

    No Known Activations