© 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. 16336
    Prev
    Next
    INDEX
    Explanations

    instances of product names related to computing devices, particularly focusing on various models and configurations of laptops and tablets

    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
    .scalablytyped
    -0.11
     componentName
    -0.09
    è¥
    -0.07
    à¤Ĺल
    -0.07
    usal
    -0.07
    plits
    -0.07
    udes
    -0.07
    burgh
    -0.07
    weet
    -0.07
    lasses
    -0.07
    POSITIVE LOGITS
     series
    0.08
     Series
    0.07
    -series
    0.06
    long
    0.06
    series
    0.06
     silhouette
    0.06
    actor
    0.06
    amp
    0.06
     série
    0.06
    одо
    0.06
    Activations Density 0.001%

    No Known Activations