© 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. 774
    Prev
    Next
    INDEX
    Explanations

    terms related to online multiplayer gameplay and interactions

    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
    lect
    -0.06
     Blackburn
    -0.06
    assi
    -0.06
    omor
    -0.06
     competitor
    -0.06
    ivor
    -0.06
    eme
    -0.06
    empor
    -0.06
     Gould
    -0.06
    usiness
    -0.05
    POSITIVE LOGITS
     ëĤĺê°Ģ
    0.07
    alse
    0.07
    .hm
    0.07
    Solo
    0.06
    CustomAttributes
    0.06
    AXB
    0.06
    ãĥ³ãĤ¸
    0.06
    .Random
    0.06
     sÃłng
    0.06
     parties
    0.06
    Activations Density 0.002%

    No Known Activations