© 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. 93642
    Prev
    Next
    INDEX
    Explanations

    references to economic and political systems, particularly capitalism

    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
    æĤ
    -0.07
    ovat
    -0.07
    odont
    -0.07
     Calder
    -0.07
    stu
    -0.07
    odon
    -0.07
    ython
    -0.06
    orr
    -0.06
    ëĶ©
    -0.06
    анг
    -0.06
    POSITIVE LOGITS
     fault
    0.07
    fault
    0.07
     writ
    0.07
     Fault
    0.07
    Primitive
    0.06
     talking
    0.06
    Triple
    0.06
    ayas
    0.06
    serter
    0.06
    748
    0.06
    Activations Density 0.066%

    No Known Activations