© 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. 687
    Prev
    Next
    INDEX
    Explanations

    references to local and international business engagement and partnerships

    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
    коÑĤ
    -0.07
    mere
    -0.07
    -columns
    -0.06
    olum
    -0.06
    ware
    -0.06
    loha
    -0.06
    alis
    -0.06
    ï¸
    -0.06
    ÌĢ
    -0.06
    nila
    -0.06
    POSITIVE LOGITS
    707
    0.07
    ezier
    0.07
    Ậ
    0.06
     TMPro
    0.06
    rys
    0.06
    houette
    0.06
     crowds
    0.06
     powerhouse
    0.06
    ropy
    0.06
    ichert
    0.06
    Activations Density 0.048%

    No Known Activations