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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 62493
    Prev
    Next
    INDEX
    Explanations

    references to injuries and medical conditions related to accidents

    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
    archives
    -0.07
    enstein
    -0.07
    avr
    -0.06
    ãĤ»ãĥĥãĥĪ
    -0.06
    agents
    -0.06
    ÑĢÑĥÑĩ
    -0.06
    CEPT
    -0.06
    ĵ
    -0.06
     yok
    -0.06
    еÑĢÑĪ
    -0.06
    POSITIVE LOGITS
     recovery
    0.07
    ánd
    0.06
    mund
    0.06
     Recovery
    0.06
    mando
    0.06
    ÙĨتÛĮ
    0.06
     Alloc
    0.06
    @js
    0.06
    onation
    0.06
    rud
    0.06
    Activations Density 0.014%

    No Known Activations