© 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. 78690
    Prev
    Next
    INDEX
    Explanations

    terms related to achievements and positive contributions in various fields

    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
    orem
    -0.07
    umont
    -0.07
    ANDOM
    -0.07
     phạm
    -0.06
    iagnostics
    -0.06
    endar
    -0.06
    ä¸Ģå®ļ
    -0.06
    οÏħÏģγ
    -0.06
    stellung
    -0.06
    jam
    -0.06
    POSITIVE LOGITS
    many
    0.07
    615
    0.07
    âĸį
    0.07
    LOTS
    0.07
    isky
    0.06
    odom
    0.06
    EEP
    0.06
     pieces
    0.06
    -many
    0.06
     khác
    0.06
    Activations Density 0.109%

    No Known Activations