© 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. 9-LLAMASCOPE-RES-131K
    11. 95619
    Prev
    Next
    INDEX
    Explanations

    references to injury or trauma-related terms

    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
    avor
    -0.08
    ushima
    -0.07
    .ht
    -0.07
    iesel
    -0.07
     preferredStyle
    -0.07
    azo
    -0.06
    акон
    -0.06
    adies
    -0.06
    ãģ¤ãģ¶
    -0.06
    141
    -0.06
    POSITIVE LOGITS
    ój
    0.06
     Fach
    0.06
     on
    0.06
     DDS
    0.05
    ilerek
    0.05
     Soy
    0.05
     è²
    0.05
     Hoff
    0.05
     bel
    0.05
     removal
    0.05
    Activations Density 0.098%

    No Known Activations