© 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. 87997
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time or sequences of 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
    .scalablytyped
    -0.10
    ãĢģãĢģ
    -0.07
    åıĬåħ¶
    -0.07
    /**č↵
    -0.06
    åĴĮ
    -0.06
     either
    -0.06
    /MPL
    -0.06
    ãĢģ↵
    -0.06
     både
    -0.06
    .ud
    -0.06
    POSITIVE LOGITS
    rogen
    0.09
     importantly
    0.08
    obe
    0.07
     therefore
    0.07
     possibly
    0.07
    leta
    0.06
    /sdk
    0.06
    ÑĶм
    0.06
     certainly
    0.06
    reso
    0.06
    Activations Density 0.025%

    No Known Activations