© 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. 28247
    Prev
    Next
    INDEX
    Explanations

    references to miraculous events or concepts

    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
     smr
    -0.07
    esi
    -0.07
    ore
    -0.07
    çĪµ
    -0.07
    ilet
    -0.06
    kaar
    -0.06
    nya
    -0.06
    loor
    -0.06
    chu
    -0.06
    Ùij
    -0.06
    POSITIVE LOGITS
    ously
    0.09
    illis
    0.08
    -working
    0.08
    ulously
    0.07
    pus
    0.07
    ully
    0.06
    plex
    0.06
    830
    0.06
    uous
    0.06
    avit
    0.06
    Activations Density 0.003%

    No Known Activations