© 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. 88809
    Prev
    Next
    INDEX
    Explanations

    references to questioning faith or divine abandonment

    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
     Kund
    -0.07
     Strom
    -0.06
    .OP
    -0.06
     round
    -0.06
    hrad
    -0.06
    à¥ģब
    -0.06
     py
    -0.06
    859
    -0.06
    zk
    -0.06
     replen
    -0.06
    POSITIVE LOGITS
    fabric
    0.07
    iž
    0.07
    ÙĬØ«
    0.07
    ingroup
    0.07
     Fabric
    0.06
    Fabric
    0.06
    isci
    0.06
    kola
    0.06
    inn
    0.06
     Bucket
    0.06
    Activations Density 0.002%

    No Known Activations