© 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. 83476
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intentions or objectives, particularly involving programs or initiatives

    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
    ster
    -0.07
    gett
    -0.06
    tha
    -0.06
     vene
    -0.05
    acus
    -0.05
    luk
    -0.05
     or
    -0.05
    gı
    -0.05
    ENO
    -0.05
    oom
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
    togroup
    0.09
    inkle
    0.08
    TYPO
    0.08
    .updateDynamic
    0.08
    Vtbl
    0.07
    GenerationStrategy
    0.07
    ssel
    0.07
    iParam
    0.07
    ='".
    0.07
    Activations Density 0.009%

    No Known Activations