© 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. 18775
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data management and persistence in gaming 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
     Slack
    -0.06
    checks
    -0.06
    omain
    -0.06
    çŃĭ
    -0.06
     slack
    -0.06
     masking
    -0.06
    .truth
    -0.06
     zast
    -0.06
     Masks
    -0.06
     代
    -0.06
    POSITIVE LOGITS
     perman
    0.13
     permanent
    0.10
    ä¿ĿåŃĺ
    0.10
     saved
    0.10
     store
    0.10
    æ°¸ä¹ħ
    0.10
     save
    0.10
     saves
    0.10
     storage
    0.10
     Permanent
    0.10
    Activations Density 0.077%

    No Known Activations