© 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. 22-LLAMASCOPE-RES-131K
    11. 4292
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and processes

    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
     Ced
    -0.07
     ad
    -0.07
    íĹĪ
    -0.06
    ammer
    -0.06
     Echo
    -0.06
    vem
    -0.06
     Wind
    -0.05
    ames
    -0.05
     Velvet
    -0.05
     helium
    -0.05
    POSITIVE LOGITS
     acids
    0.14
     киÑģлоÑĤ
    0.14
     acid
    0.13
    acid
    0.12
     Acid
    0.12
     corros
    0.12
     acidic
    0.10
    solution
    0.10
    éħ¸
    0.09
     solutions
    0.09
    Activations Density 0.031%

    No Known Activations