© 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. 84597
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to electronic circuits and systems

    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
     tavs
    -0.07
    ÃŃÅ¡
    -0.06
    adel
    -0.06
    engin
    -0.06
     Sessions
    -0.06
    CppClass
    -0.06
     سÙĦاÙħ
    -0.06
    ARRIER
    -0.06
    hip
    -0.06
    enco
    -0.06
    POSITIVE LOGITS
     connect
    0.12
    connected
    0.09
     connects
    0.09
    connect
    0.09
    .connect
    0.09
     Connect
    0.09
     connected
    0.09
     directly
    0.09
    Connected
    0.09
     Connected
    0.09
    Activations Density 0.073%

    No Known Activations