© 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. 15-LLAMASCOPE-RES-131K
    11. 90031
    Prev
    Next
    INDEX
    Explanations

    references to European cultural practices and differences

    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
    ijn
    -0.06
     Sne
    -0.06
    ylon
    -0.06
    olan
    -0.06
    ndl
    -0.05
    elly
    -0.05
    ikk
    -0.05
    ÈĻi
    -0.05
    vd
    -0.05
    éĥ
    -0.05
    POSITIVE LOGITS
     American
    0.11
     Americans
    0.09
    American
    0.09
     Amerikan
    0.09
    merican
    0.08
     амеÑĢикан
    0.08
     English
    0.08
     Amerik
    0.08
    ç¾İåĽ½
    0.08
    Americans
    0.08
    Activations Density 0.090%

    No Known Activations