© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27579
    Prev
    Next
    INDEX
    Explanations

    references to significant historical events and celebrities related to disasters

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    urga
    -0.08
    .Slf
    -0.08
    ulumi
    -0.07
    eum
    -0.07
    еко
    -0.07
    inou
    -0.07
    iculo
    -0.07
    alom
    -0.06
    OVE
    -0.06
    esini
    -0.06
    POSITIVE LOGITS
     crash
    0.09
     accident
    0.09
     loss
    0.08
     disaster
    0.07
    loss
    0.07
     crashed
    0.07
     losses
    0.07
    coll
    0.07
     tragedy
    0.07
     coach
    0.07
    Activations Density 0.072%

    No Known Activations