© 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. 106042
    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
     personal
    -0.07
     Personal
    -0.06
    ohl
    -0.06
    iffe
    -0.06
     being
    -0.06
    425
    -0.06
    ilog
    -0.05
    _skb
    -0.05
    arak
    -0.05
    iêng
    -0.05
    POSITIVE LOGITS
    icana
    0.08
    одо
    0.07
    ît
    0.07
    ุà¸Ĺ
    0.07
    utzer
    0.07
    ¶Į
    0.07
     elbow
    0.06
    опол
    0.06
    pio
    0.06
     atleast
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.