© 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. 119031
    Prev
    Next
    INDEX
    Explanations

    terms associated with regulations and legal conditions related to applications and investments

    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
    naÄį
    -0.07
     Independence
    -0.06
    iates
    -0.06
    Independ
    -0.06
    è²´
    -0.06
    itals
    -0.06
    @Bean
    -0.06
    ceipt
    -0.06
     Tie
    -0.06
     ï¼
    -0.06
    POSITIVE LOGITS
     scrutiny
    0.13
     whims
    0.07
    ÏĦον
    0.07
     pressures
    0.07
    zet
    0.07
    sty
    0.07
     constraints
    0.07
    лÑİ
    0.07
    constraints
    0.07
    isty
    0.06
    Activations Density 0.042%

    No Known Activations