© 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. 106921
    Prev
    Next
    INDEX
    Explanations

    German words or phrases

    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
    jvu
    -0.07
    odb
    -0.07
     Lag
    -0.07
     APPLY
    -0.06
    elden
    -0.06
    angel
    -0.06
    enthal
    -0.06
    ConfigurationException
    -0.06
    ascus
    -0.06
    -ng
    -0.06
    POSITIVE LOGITS
    hausen
    0.06
    anken
    0.06
    à¹ĥà¸ģล
    0.06
     Duncan
    0.06
    emy
    0.06
    elong
    0.06
     Dice
    0.06
    ÑĢой
    0.06
    ÑĢазд
    0.06
    ãĥ¼ãĥĩ
    0.06
    Activations Density 0.011%

    No Known Activations