© 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. 83983
    Prev
    Next
    INDEX
    Explanations

    conditional statements and queries about implications

    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
    -invalid
    -0.06
     lots
    -0.06
     Offline
    -0.05
    ifecycle
    -0.05
     US
    -0.05
     sending
    -0.05
     âĢİ
    -0.05
    -0.05
    xl
    -0.05
     thanks
    -0.05
    POSITIVE LOGITS
    hos
    0.08
    iture
    0.07
    erli
    0.07
    á¿ĸ
    0.07
    itat
    0.07
     OTHERWISE
    0.07
    Ø´ÙĪ
    0.07
    ÙĨÙĬÙĨ
    0.07
    eldom
    0.07
    strap
    0.07
    Activations Density 0.000%

    No Known Activations