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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1018
    Prev
    Next
    INDEX
    Explanations

    terms related to the Catholic Church and its leadership

    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
    ONO
    -0.07
    å·ŀ
    -0.07
     Isles
    -0.06
    èĴ
    -0.06
    cea
    -0.06
    State
    -0.06
    odont
    -0.06
    çĩ
    -0.06
     state
    -0.06
    ẫ
    -0.06
    POSITIVE LOGITS
    tober
    0.08
    ilenames
    0.07
    Ñĩина
    0.07
    enstein
    0.07
    esan
    0.06
    hop
    0.06
    Nonce
    0.06
    amarin
    0.06
    arendra
    0.06
    ære
    0.06
    Activations Density 0.004%

    No Known Activations