© 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. 40149
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical wiring and connection 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
    prung
    -0.06
     dynamics
    -0.06
    ypi
    -0.06
    IPA
    -0.06
     гем
    -0.06
     Cra
    -0.06
    онÑĮ
    -0.06
    ahn
    -0.05
     thr
    -0.05
    転
    -0.05
    POSITIVE LOGITS
     lineman
    0.07
     energ
    0.07
     Cable
    0.07
     splice
    0.07
     Lange
    0.07
     Fiber
    0.07
    rowsable
    0.06
    .pretty
    0.06
    ocab
    0.06
    Enumerator
    0.06
    Activations Density 0.048%

    No Known Activations