© 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. 93587
    Prev
    Next
    INDEX
    Explanations

    numerical values related to contact information or addresses

    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
    ripp
    -0.07
    erable
    -0.06
    μή
    -0.06
     tieten
    -0.06
     activation
    -0.06
     pus
    -0.06
    ÙĦØ·
    -0.06
     Leonard
    -0.06
    meter
    -0.06
     eo
    -0.06
    POSITIVE LOGITS
    à¸Ķร
    0.07
    ä»ĵ
    0.06
    bsolute
    0.06
     Peaks
    0.06
     Draco
    0.06
    ìķ½
    0.06
     Computes
    0.06
    vatel
    0.06
    PMENT
    0.06
    ÑĤи
    0.06
    Activations Density 0.012%

    No Known Activations