© 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. 70540
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate initiation or beginning of actions

    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
    vit
    -0.07
    ameda
    -0.07
    ould
    -0.06
    PUR
    -0.06
    loys
    -0.06
    Ing
    -0.06
    δή
    -0.06
    daÅŁ
    -0.06
    dit
    -0.06
    δα
    -0.06
    POSITIVE LOGITS
     with
    0.08
    nings
    0.08
    670
    0.07
    activex
    0.07
    äºĭæ¥Ń
    0.07
    376
    0.06
     Gibbs
    0.06
    istant
    0.06
     dengan
    0.06
    acz
    0.06
    Activations Density 0.005%

    No Known Activations