© 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 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. 119326
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions or colleges

    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
     demokrat
    -0.06
    ibold
    -0.06
    yd
    -0.06
    ῦ
    -0.06
    BJ
    -0.06
    ACS
    -0.06
    _MASTER
    -0.06
    Ðĭ
    -0.06
     Mev
    -0.06
     deed
    -0.06
    POSITIVE LOGITS
    ue
    0.08
    ory
    0.08
    ues
    0.08
    chia
    0.07
    amento
    0.07
    ued
    0.06
    hee
    0.06
    amenti
    0.06
    lobals
    0.06
    hey
    0.06
    Activations Density 0.002%

    No Known Activations