© 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. 87852
    Prev
    Next
    INDEX
    Explanations

    legislative references and associated numbers

    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
    putation
    -0.06
    æĿIJ
    -0.06
    ýt
    -0.06
    iana
    -0.06
    luvÃŃ
    -0.05
    aydı
    -0.05
    olars
    -0.05
    apt
    -0.05
    lass
    -0.05
    bett
    -0.05
    POSITIVE LOGITS
    anja
    0.07
    éré
    0.07
    atori
    0.07
    phans
    0.07
    band
    0.07
    ضر
    0.07
     ihtiy
    0.07
     desn
    0.07
     fich
    0.07
    442
    0.06
    Activations Density 0.023%

    No Known Activations