© 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. 61229
    Prev
    Next
    INDEX
    Explanations

    elements related to discussions and decisions in a competitive 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
     Transit
    -0.07
     transit
    -0.07
    inking
    -0.06
     schem
    -0.06
    ilder
    -0.06
    inki
    -0.06
     æŁ
    -0.06
     Depths
    -0.06
    weeks
    -0.05
    à¸ļาà¸Ĺ
    -0.05
    POSITIVE LOGITS
    浪
    0.08
    /weather
    0.08
    ế
    0.07
    鼨
    0.07
    xon
    0.07
     rain
    0.07
    oplay
    0.07
     Weather
    0.07
    _weather
    0.07
    -cond
    0.07
    Activations Density 0.005%

    No Known Activations