© 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. 90156
    Prev
    Next
    INDEX
    Explanations

    specific terminology related to gaming and regulatory frameworks

    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
    æ²»
    -0.07
    Certain
    -0.06
     almost
    -0.06
    ve
    -0.06
    iker
    -0.06
    ÏĥÏĦο
    -0.06
     nạn
    -0.06
    æīįèĥ½
    -0.06
    ker
    -0.06
     Camp
    -0.06
    POSITIVE LOGITS
     nor
    0.17
    nor
    0.12
     anymore
    0.11
     ani
    0.09
     NOR
    0.09
     Nor
    0.08
     neither
    0.08
    Nor
    0.08
     necessarily
    0.07
     nors
    0.07
    Activations Density 0.021%

    No Known Activations