© 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. 116346
    Prev
    Next
    INDEX
    Explanations

    references to rescue operations and survival in disaster situations

    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
    .Sdk
    -0.08
    Patch
    -0.08
    .patch
    -0.08
    patch
    -0.08
    SystemService
    -0.07
    )prepare
    -0.07
     Patch
    -0.07
    RAIN
    -0.07
    itmap
    -0.07
    hart
    -0.07
    POSITIVE LOGITS
     collapse
    0.13
     collapses
    0.12
    collapse
    0.12
     collapsed
    0.10
     Collapse
    0.10
    -collapse
    0.10
     rubble
    0.09
     building
    0.09
     collapsing
    0.09
     demolition
    0.08
    Activations Density 0.075%

    No Known Activations