© 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. 93495
    Prev
    Next
    INDEX
    Explanations

    terms related to home improvement and electrical work

    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
    aggable
    -0.07
    inee
    -0.07
    abilia
    -0.07
    islav
    -0.07
    terdam
    -0.07
    ephy
    -0.07
    ervers
    -0.07
    acements
    -0.07
    (æ°´
    -0.07
    urve
    -0.06
    POSITIVE LOGITS
     diagnose
    0.06
    di
    0.06
    alle
    0.06
     louder
    0.06
     diagnosis
    0.06
    ass
    0.06
    js
    0.06
    à¥Ĥà¤ķ
    0.06
    è¯Ĭ
    0.06
     Rhodes
    0.05
    Activations Density 0.001%

    No Known Activations