© 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. 60862
    Prev
    Next
    INDEX
    Explanations

    references to railings and safety features in architectural contexts

    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
     straw
    -0.08
    çª
    -0.07
    ccione
    -0.07
    ãģĻãģĻ
    -0.07
     NDEBUG
    -0.07
     BoxFit
    -0.07
     Insecta
    -0.07
    vä
    -0.07
     Diagnostic
    -0.06
    ÑģÑĭл
    -0.06
    POSITIVE LOGITS
     Safety
    0.07
     safety
    0.07
    afety
    0.07
    Safety
    0.07
    -height
    0.07
     stair
    0.07
     Cable
    0.06
    inst
    0.06
     pedestrian
    0.06
    hog
    0.06
    Activations Density 0.001%

    No Known Activations