© 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. 5-LLAMASCOPE-RES-131K
    11. 126414
    Prev
    Next
    INDEX
    Explanations

    references to CSS stylesheets

    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
    ore
    -0.07
     unders
    -0.07
    aginator
    -0.06
     rec
    -0.06
    uri
    -0.06
    uded
    -0.06
     reserve
    -0.05
    won
    -0.05
     elect
    -0.05
     lk
    -0.05
    POSITIVE LOGITS
    ekl
    0.07
    eldo
    0.07
    اÙħÛĮÙĨ
    0.07
    ³
    0.07
    istring
    0.07
    aldo
    0.07
    akers
    0.07
    æ·»
    0.06
     Aires
    0.06
     Sachs
    0.06
    Activations Density 0.001%

    No Known Activations