© 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. 91769
    Prev
    Next
    INDEX
    Explanations

    terms related to bridges and infrastructure

    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
    RITE
    -0.07
    jang
    -0.07
    اÙĬد
    -0.07
     Shank
    -0.06
    shal
    -0.06
     nouve
    -0.06
     GetLastError
    -0.06
    í
    -0.06
    sass
    -0.06
    оÑī
    -0.06
    POSITIVE LOGITS
     block
    0.12
    -block
    0.11
     blocking
    0.10
    block
    0.10
     blocked
    0.10
     jam
    0.10
     blockade
    0.09
     Blocking
    0.09
    -blocking
    0.09
     blocks
    0.09
    Activations Density 0.040%

    No Known Activations