© 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. 3747
    Prev
    Next
    INDEX
    Explanations

    discussions about the importance of art, creativity, and collaboration

    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
    disposing
    -0.08
    rani
    -0.08
    缤
    -0.07
    ÃŃ
    -0.07
    oku
    -0.07
    oca
    -0.07
     Ñĥли
    -0.07
    igli
    -0.07
    isha
    -0.06
     Vinci
    -0.06
    POSITIVE LOGITS
     audience
    0.09
     Audience
    0.06
    ÑĢов
    0.06
     audiences
    0.06
     (;;)
    0.06
     patron
    0.06
     reception
    0.06
    inished
    0.06
     writing
    0.05
     ngÃłnh
    0.05
    Activations Density 0.151%

    No Known Activations