© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 5248
    Prev
    Next
    INDEX
    Explanations

    themes related to divine or spiritual elements intertwined with communal aspects or human relationships

    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
    åĽ
    -0.07
    pit
    -0.06
    _FATAL
    -0.06
    ISTER
    -0.06
     Kut
    -0.06
    CEF
    -0.06
    494
    -0.06
     Pit
    -0.06
    holm
    -0.06
    ãĤ¹ãĤ¯
    -0.06
    POSITIVE LOGITS
    å¾Ĺ
    0.08
    ponses
    0.06
     Singleton
    0.06
    à¸Īะà¹Ħà¸Ķ
    0.06
    reu
    0.06
    029
    0.06
    rij
    0.06
    475
    0.06
     ìĸ»
    0.06
     learn
    0.06
    Activations Density 0.025%

    No Known Activations