© 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. 16662
    Prev
    Next
    INDEX
    Explanations

    references to governmental ministries or departments

    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
    oteca
    -0.07
    loff
    -0.07
    335
    -0.06
    StackNavigator
    -0.06
    mong
    -0.06
    ngle
    -0.06
    λλα
    -0.06
     вз
    -0.06
    *sizeof
    -0.06
    mdi
    -0.06
    POSITIVE LOGITS
     finance
    0.09
     Finance
    0.09
    eller
    0.08
     Ãĩev
    0.07
    finance
    0.07
    marshall
    0.07
     Supplies
    0.07
     bò
    0.07
    KI
    0.06
    ãĤ¥
    0.06
    Activations Density 0.010%

    No Known Activations