© 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. 78284
    Prev
    Next
    INDEX
    Explanations

    issues related to government and religion intersection

    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
    assin
    -0.08
    AFX
    -0.07
    cargo
    -0.07
    声
    -0.07
    POSIT
    -0.07
    agara
    -0.06
    íĮĮíĬ¸
    -0.06
    ยาà¸Ļ
    -0.06
    /setup
    -0.06
    IBE
    -0.06
    POSITIVE LOGITS
     Anim
    0.07
     anim
    0.06
     Wedding
    0.06
     Muhammad
    0.06
    uir
    0.06
     customers
    0.06
     customer
    0.06
     rainbow
    0.06
    storm
    0.06
     ê³łê°Ŀ
    0.06
    Activations Density 0.001%

    No Known Activations