© 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. 3776
    Prev
    Next
    INDEX
    Explanations

    temporal phrases or references related to events occurring over time

    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
    ä¹ħ
    -0.08
    ewis
    -0.08
    .scalablytyped
    -0.08
    вид
    -0.06
    CLU
    -0.06
    ulaire
    -0.06
    .IContainer
    -0.06
    berapa
    -0.06
    idge
    -0.06
    ixer
    -0.06
    POSITIVE LOGITS
     midst
    0.08
     already
    0.08
     exactly
    0.08
     precisely
    0.07
     still
    0.07
    æŃ£åľ¨
    0.07
    still
    0.07
    bew
    0.07
    ekt
    0.07
    enk
    0.07
    Activations Density 0.024%

    No Known Activations