© 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. 79188
    Prev
    Next
    INDEX
    Explanations

    phrases that denote being affected or influenced by various factors or entities

    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
    .easing
    -0.08
    _Collections
    -0.08
    inize
    -0.08
    .LENGTH
    -0.07
     æ¥
    -0.07
    ADR
    -0.07
    iry
    -0.07
     namoro
    -0.07
     Ñģебе
    -0.07
    ฤ
    -0.07
    POSITIVE LOGITS
    jon
    0.06
    ross
    0.06
    ernal
    0.06
    105
    0.06
    ros
    0.05
    waves
    0.05
     dormant
    0.05
    ump
    0.05
    rus
    0.05
    obra
    0.05
    Activations Density 0.029%

    No Known Activations