© 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. 15-LLAMASCOPE-RES-131K
    11. 62002
    Prev
    Next
    INDEX
    Explanations

    sections of legal or regulatory text

    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
    acted
    -0.06
    ports
    -0.06
    izer
    -0.06
    aday
    -0.05
     cherry
    -0.05
     slow
    -0.05
     Case
    -0.05
    loop
    -0.05
    bab
    -0.05
     case
    -0.05
    POSITIVE LOGITS
    resco
    0.08
    åĬ
    0.08
     ÑĤÑı
    0.08
    chwitz
    0.07
     UIScreen
    0.07
    smarty
    0.07
    å¼ķãģį
    0.07
    usan
    0.07
    bservice
    0.07
    еÑĢин
    0.07
    Activations Density 0.003%

    No Known Activations