© 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. 86707
    Prev
    Next
    INDEX
    Explanations

    concepts related to economic transfer and questions

    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
    MBProgressHUD
    -0.07
    eyim
    -0.06
    جÙħ
    -0.06
     îł
    -0.06
    олÑĮ
    -0.06
    ONA
    -0.06
    нÑĶ
    -0.06
    AGR
    -0.06
     Grace
    -0.06
    opr
    -0.06
    POSITIVE LOGITS
    kker
    0.07
    icks
    0.07
    Ñĥз
    0.07
    oggled
    0.07
    _stderr
    0.06
    xes
    0.06
    ominated
    0.06
    ipse
    0.06
    -нибÑĥдÑĮ
    0.06
    otation
    0.06
    Activations Density 0.000%

    No Known Activations