© 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. 129031
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to angular resolution measurements in scientific data

    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
    atik
    -0.07
    nul
    -0.07
    _SAFE
    -0.06
    à¥ĩष
    -0.06
     maxHeight
    -0.06
    rim
    -0.06
    kır
    -0.06
    åıijçĶŁ
    -0.06
     ÏĢ
    -0.06
    assage
    -0.06
    POSITIVE LOGITS
     accuracy
    0.08
     improvement
    0.07
     precision
    0.07
     resolution
    0.07
     rootReducer
    0.07
     Improvement
    0.07
     quality
    0.07
     verbess
    0.06
    è³¢
    0.06
     resolving
    0.06
    Activations Density 0.107%

    No Known Activations