© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 87649
    Prev
    Next
    INDEX
    Explanations

    phrases related to collective experiences and shared activities

    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
    eteria
    -0.06
    ael
    -0.06
    kami
    -0.06
    _cli
    -0.05
    cli
    -0.05
    -animate
    -0.05
     nobody
    -0.05
     system
    -0.05
    toc
    -0.05
    582
    -0.05
    POSITIVE LOGITS
    baugh
    0.07
    olut
    0.07
     Shame
    0.07
     æĬķ稿
    0.07
     lai
    0.07
    jt
    0.07
    abbo
    0.07
    279
    0.07
    شار
    0.07
    ç½ļ
    0.06
    Activations Density 0.002%

    No Known Activations