© 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. 116550
    Prev
    Next
    INDEX
    Explanations

    specific individuals and their achievements in competitive contexts

    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
    iele
    -0.08
    fw
    -0.07
     neighbouring
    -0.07
    ISTA
    -0.06
    iale
    -0.06
    Ey
    -0.06
    ãĥ©ãĤ¤ãĥĪ
    -0.06
     neighboring
    -0.06
    rito
    -0.06
    oney
    -0.06
    POSITIVE LOGITS
    å°ĭ
    0.07
     previously
    0.07
     previous
    0.07
     adipiscing
    0.07
    ccione
    0.07
    éĤĬ
    0.07
     æ¾
    0.06
     earlier
    0.06
    roid
    0.06
    udio
    0.06
    Activations Density 0.016%

    No Known Activations