© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126788
    Prev
    Next
    INDEX
    Explanations

    references to divine teaching and the role of God in life

    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
    gregar
    -0.07
    Ľ°
    -0.07
    deaux
    -0.07
    reib
    -0.07
    oux
    -0.07
    ERİ
    -0.07
    lena
    -0.06
    оÑĢи
    -0.06
    ÏħÏĥ
    -0.06
     stretch
    -0.06
    POSITIVE LOGITS
    adel
    0.07
    лÑĥ
    0.06
    raz
    0.06
     Wet
    0.06
    andon
    0.06
     zaj
    0.06
    кÑĥп
    0.06
    ief
    0.06
    biz
    0.06
    anda
    0.06
    Activations Density 0.004%

    No Known Activations