© 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. 22-LLAMASCOPE-RES-131K
    11. 4262
    Prev
    Next
    INDEX
    Explanations

    references to divinity and religious 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
    ç¤
    -0.07
    woff
    -0.07
    .Reporting
    -0.07
     ÐľÑĸнÑĸÑģÑĤеÑĢ
    -0.06
    enk
    -0.06
    xico
    -0.06
    ãĥ©ãĥĥãĤ¯
    -0.06
     Reporting
    -0.06
    //{{
    -0.06
    ее
    -0.06
    POSITIVE LOGITS
     desire
    0.08
     alone
    0.07
     gave
    0.07
     died
    0.07
    brew
    0.07
     wanting
    0.06
     reign
    0.06
     ÙģرÙħÙĪد
    0.06
     knew
    0.06
     reward
    0.06
    Activations Density 0.017%

    No Known Activations