© 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. 5-LLAMASCOPE-RES-131K
    11. 126083
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the significance of divine guidance and motivation

    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
    reau
    -0.09
    idal
    -0.07
    ÙħÙĦ
    -0.07
    riel
    -0.07
    erala
    -0.07
    istik
    -0.07
    mong
    -0.07
     Compatibility
    -0.06
    ikal
    -0.06
    igid
    -0.06
    POSITIVE LOGITS
    .retry
    0.07
     dep
    0.06
    _unix
    0.06
     UNU
    0.06
     rebate
    0.06
    .github
    0.05
    .resource
    0.05
    urname
    0.05
    eper
    0.05
    -et
    0.05
    Activations Density 0.008%

    No Known Activations