© 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. 17-LLAMASCOPE-RES-131K
    11. 62854
    Prev
    Next
    INDEX
    Explanations

    mention of formal events or ceremonies

    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
    orna
    -0.07
    ëģĶ
    -0.07
    side
    -0.07
    tember
    -0.07
    eko
    -0.07
    ÙĪب
    -0.07
    家çļĦ
    -0.06
    smith
    -0.06
    480
    -0.06
    ers
    -0.06
    POSITIVE LOGITS
    ivals
    0.08
    ault
    0.08
    οÏħÏģγ
    0.07
    .googlecode
    0.07
    emony
    0.07
    -vous
    0.07
    altung
    0.07
    uploaded
    0.07
     conducted
    0.07
    usalem
    0.07
    Activations Density 0.006%

    No Known Activations