© 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. 30781
    Prev
    Next
    INDEX
    Explanations

    references to cultural or spiritual significance and the reasons behind respect for them

    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
    abo
    -0.07
    IPA
    -0.06
    æİĮ
    -0.06
    angi
    -0.06
    евÑĸ
    -0.06
    itur
    -0.06
     Mell
    -0.06
    abol
    -0.06
     Seah
    -0.06
    arch
    -0.06
    POSITIVE LOGITS
     reasons
    0.13
     differently
    0.12
     different
    0.10
     Reasons
    0.10
    different
    0.09
    åİŁåĽł
    0.08
     opposite
    0.08
     Different
    0.08
    Reason
    0.08
     wrong
    0.07
    Activations Density 0.054%

    No Known Activations