© 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. 15-LLAMASCOPE-RES-131K
    11. 86777
    Prev
    Next
    INDEX
    Explanations

    phrases related to divine or spiritual authority

    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
    itive
    -0.06
    å½¢
    -0.06
    uras
    -0.06
    arat
    -0.06
    524
    -0.06
    ell
    -0.06
    imm
    -0.06
     Wien
    -0.06
    .tar
    -0.06
    ness
    -0.06
    POSITIVE LOGITS
    okit
    0.08
    CDATA
    0.08
    CALE
    0.07
    viso
    0.07
    entiful
    0.07
    ataire
    0.07
    _OM
    0.07
    ivement
    0.07
    .WinForms
    0.07
    chandle
    0.06
    Activations Density 0.018%

    No Known Activations