© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76250
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical and wave phenomena

    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
    ABCDE
    -0.08
    sek
    -0.07
    .wind
    -0.07
    syscall
    -0.07
    .synthetic
    -0.07
    olics
    -0.07
    itchen
    -0.06
    etch
    -0.06
     Star
    -0.06
     diplomatic
    -0.06
    POSITIVE LOGITS
     passage
    0.08
     electrons
    0.08
     carriers
    0.07
     passages
    0.07
     passing
    0.07
     electrical
    0.07
    鼻åŃIJ
    0.07
     carrier
    0.07
     electronic
    0.07
     elektron
    0.07
    Activations Density 0.015%

    No Known Activations