© 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. 123330
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical references

    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
    ichten
    -0.06
    34
    -0.06
    icus
    -0.06
    ber
    -0.06
    334
    -0.06
    biz
    -0.06
     partial
    -0.05
     reversible
    -0.05
    ãģĤãĤĬãģĮãģ¨ãģĨ
    -0.05
     banner
    -0.05
    POSITIVE LOGITS
    allis
    0.09
    csi
    0.08
     ë¹Ī
    0.07
    Empty
    0.07
    .BL
    0.07
    ienne
    0.07
    .Generated
    0.07
    ãİ
    0.07
    /sbin
    0.07
     Coastal
    0.07
    Activations Density 0.003%

    No Known Activations