© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75662
    Prev
    Next
    INDEX
    Explanations

    technical terms related to vehicle mechanics

    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
    ooter
    -0.07
    rier
    -0.07
    usercontent
    -0.07
    ĻĤ
    -0.07
    fik
    -0.07
    phants
    -0.07
    anden
    -0.07
     Daly
    -0.07
    itzer
    -0.06
    ago
    -0.06
    POSITIVE LOGITS
     Safety
    0.07
     safety
    0.06
    Unsafe
    0.06
    pus
    0.06
    Safety
    0.06
     pon
    0.06
     Borg
    0.06
    оÑĢм
    0.06
    æ¡£
    0.06
     insult
    0.06
    Activations Density 0.000%

    No Known Activations