© 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. 83064
    Prev
    Next
    INDEX
    Explanations

    phrases that provide contact information or instructions for further inquiries

    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
    éģ¸æīĭ
    -0.07
    ãĤ¹ãĥĨ
    -0.07
    oppel
    -0.07
    олÑĮно
    -0.07
    ãĤĮãģ©
    -0.07
    asaki
    -0.06
    éIJ
    -0.06
    ÑĢÑĥп
    -0.06
    ĨĴ
    -0.06
    ire
    -0.06
    POSITIVE LOGITS
     call
    0.07
     www
    0.07
     Lehr
    0.06
    137
    0.06
     Call
    0.06
     Mata
    0.06
     Raw
    0.06
    (call
    0.06
     Central
    0.06
     weather
    0.06
    Activations Density 0.012%

    No Known Activations