© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126472
    Prev
    Next
    INDEX
    Explanations

    phrases related to contentment or satisfaction

    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
    sword
    -0.07
    OOM
    -0.07
    ANTE
    -0.07
    ancel
    -0.07
    \Foundation
    -0.07
    .tar
    -0.07
     Amid
    -0.07
    pard
    -0.06
    olith
    -0.06
    رØŃ
    -0.06
    POSITIVE LOGITS
    ursors
    0.06
     CN
    0.06
    -en
    0.06
     Dex
    0.06
    als
    0.06
    elve
    0.06
     Conrad
    0.05
    imits
    0.05
     couple
    0.05
     pos
    0.05
    Activations Density 0.003%

    No Known Activations