© 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. 126266
    Prev
    Next
    INDEX
    Explanations

    terms related to inhalation and ingestion methods

    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
    aversal
    -0.07
    ality
    -0.07
    AXB
    -0.07
    sheets
    -0.07
    .authenticate
    -0.07
    .scalablytyped
    -0.07
    ambi
    -0.06
    fait
    -0.06
    нÑı
    -0.06
    conexao
    -0.06
    POSITIVE LOGITS
    able
    0.09
    ables
    0.07
     breath
    0.07
    ABLE
    0.07
    æģ¯
    0.07
     breathed
    0.06
    bourne
    0.06
    çŃĴ
    0.06
     respir
    0.06
     asthma
    0.06
    Activations Density 0.002%

    No Known Activations