© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 107248
    Prev
    Next
    INDEX
    Explanations

    themes related to existential questions and struggles with faith

    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
    åį±
    -0.09
     hilar
    -0.07
    agit
    -0.07
    urtle
    -0.07
    (strpos
    -0.07
    ALSE
    -0.07
    undos
    -0.07
    pulse
    -0.07
    omo
    -0.07
    peater
    -0.07
    POSITIVE LOGITS
    wyn
    0.09
     pain
    0.07
     McA
    0.07
     God
    0.07
    tember
    0.06
     IDb
    0.06
     cancer
    0.06
    kat
    0.06
     children
    0.06
     Barrel
    0.06
    Activations Density 0.019%

    No Known Activations