© 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. 57110
    Prev
    Next
    INDEX
    Explanations

    references to divine protection and strength

    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
    itou
    -0.07
    ookies
    -0.07
    Ïĥο
    -0.07
    Ïģιά
    -0.07
    ucer
    -0.07
    .Apis
    -0.07
    upy
    -0.07
    çĤ
    -0.07
    DidLoad
    -0.07
    anz
    -0.07
    POSITIVE LOGITS
     Carey
    0.07
    ale
    0.06
    qus
    0.06
    ÙĪتر
    0.06
     evid
    0.06
     ext
    0.05
    nuts
    0.05
    pread
    0.05
     bo
    0.05
    à¥ģब
    0.05
    Activations Density 0.007%

    No Known Activations