© 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. 15-LLAMASCOPE-RES-131K
    11. 62178
    Prev
    Next
    INDEX
    Explanations

    terminology related to promptness or timeliness in actions and processes

    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
    alian
    -0.07
    linger
    -0.07
    èĩ
    -0.07
    ason
    -0.07
    Äħż
    -0.06
    stadt
    -0.06
    elf
    -0.06
    son
    -0.06
    essler
    -0.06
    asper
    -0.06
    POSITIVE LOGITS
    posables
    0.09
     manner
    0.08
    NESS
    0.08
    ร
    0.07
    lest
    0.07
    åĪ»
    0.07
    edad
    0.07
    ness
    0.07
    amente
    0.07
    ament
    0.07
    Activations Density 0.005%

    No Known Activations