© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2840
    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
    IPHER
    -0.07
     Sanayi
    -0.07
    elman
    -0.07
    431
    -0.07
    556
    -0.06
    elay
    -0.06
    .aspx
    -0.06
     amt
    -0.06
    _ENUM
    -0.06
    _ASSUME
    -0.06
    POSITIVE LOGITS
    utes
    0.07
    å¾ĭ
    0.07
    격
    0.06
    èĩ´
    0.06
    _notify
    0.06
    oot
    0.06
    ourced
    0.06
    Ø´Ùĩ
    0.06
    addock
    0.06
    okia
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.