© 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. 5-LLAMASCOPE-RES-131K
    11. 126094
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and election procedures

    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
    agi
    -0.06
    mob
    -0.06
    omb
    -0.06
    avers
    -0.06
    ael
    -0.06
    aight
    -0.06
    acro
    -0.06
    anders
    -0.06
    aign
    -0.06
     ÙĦÙĦس
    -0.06
    POSITIVE LOGITS
    imir
    0.07
    ÏģοÏįν
    0.06
     γεÏģ
    0.06
    Reusable
    0.06
    &q
    0.06
    ÏĦεÏģ
    0.06
     distr
    0.06
    >Note
    0.06
    ÄĻp
    0.06
     hostages
    0.06
    Activations Density 0.006%

    No Known Activations