© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1232
    Prev
    Next
    INDEX
    Explanations

    specific brand names or entities associated with distinct activities or products

    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
    åħ¸
    -0.06
    lili
    -0.06
    ç¦
    -0.06
    .setRotation
    -0.06
    окон
    -0.06
    amac
    -0.06
    ocos
    -0.06
    olders
    -0.06
    inu
    -0.06
    encer
    -0.06
    POSITIVE LOGITS
    \CMS
    0.08
    specific
    0.08
    ritch
    0.07
     specific
    0.06
    pora
    0.06
     tieten
    0.06
    connection
    0.06
    Å¡tÃŃ
    0.06
    -specific
    0.06
    åĶ¯
    0.06
    Activations Density 0.018%

    No Known Activations