© 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. 17-LLAMASCOPE-RES-131K
    11. 84183
    Prev
    Next
    INDEX
    Explanations

    references to spirituality and spiritual 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
    ERIC
    -0.10
    enda
    -0.07
    eriod
    -0.07
    ieties
    -0.07
    ijing
    -0.07
    ham
    -0.07
    eworthy
    -0.07
    олоÑĤ
    -0.07
    JECT
    -0.07
    antry
    -0.07
    POSITIVE LOGITS
    uality
    0.10
    ual
    0.10
    ually
    0.09
    UAL
    0.09
    uous
    0.09
    uelle
    0.08
    omen
    0.07
    uell
    0.07
    DN
    0.07
    td
    0.07
    Activations Density 0.015%

    No Known Activations