© 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. 15-LLAMASCOPE-RES-131K
    11. 103842
    Prev
    Next
    INDEX
    Explanations

    phrases related to home inspections and repairs

    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
    ัà¸ķร
    -0.06
    ì¦Ŀ
    -0.06
    positor
    -0.06
    etas
    -0.06
     Ents
    -0.06
     ActionTypes
    -0.06
    oloj
    -0.06
    lea
    -0.06
    egative
    -0.06
    imore
    -0.06
    POSITIVE LOGITS
     Minor
    0.08
     minor
    0.07
    ornado
    0.07
    egen
    0.07
     Feng
    0.06
     liv
    0.06
    ÏĢί
    0.06
     living
    0.06
     TLC
    0.06
     fixes
    0.06
    Activations Density 0.024%

    No Known Activations