© 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. 5-LLAMASCOPE-RES-131K
    11. 126104
    Prev
    Next
    INDEX
    Explanations

    references to the current day or present time context

    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
    heiten
    -0.06
    ava
    -0.05
     rest
    -0.05
     Sass
    -0.05
    onen
    -0.05
     Egg
    -0.05
    erie
    -0.05
     Fury
    -0.05
    족
    -0.05
     predict
    -0.05
    POSITIVE LOGITS
    ogn
    0.08
    ган
    0.07
    achel
    0.07
    imli
    0.07
    ãĥªãĤ«
    0.07
    acent
    0.07
    IME
    0.07
    slu
    0.07
    ByExample
    0.07
     frem
    0.07
    Activations Density 0.003%

    No Known Activations