© 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. 82710
    Prev
    Next
    INDEX
    Explanations

    numerical data related to age and significant events

    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
     Nun
    -0.07
     Barber
    -0.07
    ibbon
    -0.06
    modo
    -0.06
    bon
    -0.06
    uke
    -0.06
    .Interop
    -0.06
    icl
    -0.06
    ijľ
    -0.06
    lik
    -0.06
    POSITIVE LOGITS
    åºŃ
    0.08
    ارÙĩ
    0.06
    mÄĽ
    0.06
     Laurel
    0.06
     exem
    0.06
    elines
    0.06
    launcher
    0.06
     ãģ¿
    0.06
     OG
    0.05
    ãģĮãģĦ
    0.05
    Activations Density 0.003%

    No Known Activations