© 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. 57018
    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
    ANGO
    -0.07
    opup
    -0.06
    uset
    -0.06
    RL
    -0.06
    uby
    -0.06
    \Entities
    -0.06
     tidy
    -0.06
    iao
    -0.06
    435
    -0.06
    osten
    -0.06
    POSITIVE LOGITS
    shima
    0.06
    ानव
    0.06
    edu
    0.06
     jist
    0.06
     Silicone
    0.06
    vor
    0.06
     Www
    0.06
    лоÑĢ
    0.06
    exion
    0.06
    åļ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.