© 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. 5387
    Prev
    Next
    INDEX
    Explanations

    references to religious leaders or figures

    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
    iesel
    -0.07
    PERT
    -0.07
    kaar
    -0.07
    gether
    -0.07
    mere
    -0.07
    ÑĢеÑħ
    -0.07
    ehr
    -0.07
    asl
    -0.07
    iciel
    -0.07
    osti
    -0.06
    POSITIVE LOGITS
    ¹
    0.06
     Buccane
    0.06
    ®
    0.06
    .experimental
    0.06
    ucker
    0.06
    s
    0.06
     conscient
    0.06
    429
    0.05
    ://
    0.05
    esian
    0.05
    Activations Density 0.007%

    No Known Activations