© 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. 118067
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the beginning or starting point of events or experiences

    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
    ÑĥлÑİ
    -0.07
     later
    -0.07
    ardy
    -0.07
     behalf
    -0.07
    iguiente
    -0.07
    iek
    -0.06
    ãĥķãĥ¬
    -0.06
    å¾Įãģ®
    -0.06
    лев
    -0.06
    ëŀij
    -0.06
    POSITIVE LOGITS
     dès
    0.14
     immediately
    0.12
     moment
    0.10
     instant
    0.10
     minute
    0.10
     instantly
    0.09
     earliest
    0.09
    ë¶ĢíĦ°
    0.09
     outset
    0.09
     ÑģÑĢазÑĥ
    0.09
    Activations Density 0.069%

    No Known Activations