© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70897
    Prev
    Next
    INDEX
    Explanations

    phrases indicating communication and interaction

    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
    ALCHEMY
    -0.06
    assel
    -0.06
    èµı
    -0.06
    úc
    -0.06
     serm
    -0.06
    uku
    -0.06
     fabs
    -0.06
    à¸Ĺร
    -0.06
    076
    -0.06
     Howe
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
    šet
    0.07
    æŀĿ
    0.07
    CTS
    0.06
    laden
    0.06
    管
    0.06
     Klopp
    0.06
    777
    0.06
    .demo
    0.06
     includ
    0.06
    Activations Density 0.001%

    No Known Activations