© 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. 58206
    Prev
    Next
    INDEX
    Explanations

    references to knowledge and awareness of actions or events

    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
     вÑģпом
    -0.07
    аÑĢÑĩ
    -0.07
    setError
    -0.07
     ister
    -0.07
    ubi
    -0.07
    pcl
    -0.07
    βι
    -0.07
    ChangedEventArgs
    -0.07
    NullException
    -0.07
    κÏħ
    -0.07
    POSITIVE LOGITS
     ìķĮê³ł
    0.06
     knew
    0.06
     dangers
    0.06
     danger
    0.06
     risks
    0.06
     prob
    0.06
     early
    0.06
     warnings
    0.06
     repeatedly
    0.06
     biết
    0.05
    Activations Density 0.027%

    No Known Activations