© 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. 9-LLAMASCOPE-RES-131K
    11. 99144
    Prev
    Next
    INDEX
    Explanations

    references to communication during emergency 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
    iram
    -0.06
     Watkins
    -0.06
    vala
    -0.06
     sinc
    -0.05
    åĪ
    -0.05
    ï
    -0.05
    memberof
    -0.05
     Wheeler
    -0.05
    CF
    -0.05
     till
    -0.05
    POSITIVE LOGITS
    zano
    0.08
    oci
    0.07
    kees
    0.07
    opup
    0.07
    veis
    0.07
    .twig
    0.07
    лади
    0.07
    roys
    0.07
    usher
    0.07
    êt
    0.07
    Activations Density 0.016%

    No Known Activations