© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 93707
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    800
    -0.06
    inh
    -0.06
    978
    -0.06
     others
    -0.05
    420
    -0.05
    bek
    -0.05
     ...↵
    -0.05
    427
    -0.05
    417
    -0.05
    936
    -0.05
    POSITIVE LOGITS
    -toggler
    0.07
    -alist
    0.07
    ANDOM
    0.07
    UIAlert
    0.07
    olec
    0.07
    afil
    0.07
    íĮĮíĬ¸
    0.07
    sob
    0.07
    بÙĪØ§Ø³Ø·Ø©
    0.07
    licenses
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.