© 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. 84420
    Prev
    Next
    INDEX
    Explanations

    references to individuals or specific names within the text

    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
    .datab
    -0.08
    ıģ
    -0.07
    ÑĮÑİ
    -0.07
    iminal
    -0.07
     khung
    -0.07
    éijij
    -0.07
    anky
    -0.07
    ÑģÑĤин
    -0.07
    iot
    -0.07
    èĦ
    -0.07
    POSITIVE LOGITS
     st
    0.07
    CONF
    0.06
    kl
    0.06
    lore
    0.06
    las
    0.06
     non
    0.05
     fri
    0.05
    ki
    0.05
    ellar
    0.05
    exo
    0.05
    Activations Density 0.016%

    No Known Activations