© 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. 82800
    Prev
    Next
    INDEX
    Explanations

    user interface elements and their interactions

    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
    anst
    -0.09
    anas
    -0.08
    dzi
    -0.07
    è¼Ŀ
    -0.07
    alez
    -0.07
    ystack
    -0.07
    کتر
    -0.07
    enties
    -0.07
    asma
    -0.07
     ÄIJo
    -0.07
    POSITIVE LOGITS
     icon
    0.08
    /icon
    0.07
     circ
    0.07
    ç·
    0.07
    ê
    0.06
     shaped
    0.06
     invent
    0.06
     tiny
    0.06
     bul
    0.06
     gear
    0.06
    Activations Density 0.010%

    No Known Activations