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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57235
    Prev
    Next
    INDEX
    Explanations

    references to remembrance and mourning related to traffic victims

    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
    vote
    -0.06
    alue
    -0.06
    _mgr
    -0.06
    /cloud
    -0.06
    ported
    -0.06
    utoff
    -0.06
     encount
    -0.06
    ello
    -0.06
    beit
    -0.06
    olist
    -0.06
    POSITIVE LOGITS
     safety
    0.13
     Safety
    0.12
     crash
    0.12
     accident
    0.11
    Safety
    0.11
     accidents
    0.10
     unsafe
    0.10
     Crash
    0.10
     Traffic
    0.10
     Road
    0.10
    Activations Density 0.027%

    No Known Activations