© 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. 129703
    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
    orman
    -0.07
    ))?
    -0.07
    anc
    -0.07
    _pb
    -0.06
    Exposed
    -0.06
    FINITY
    -0.06
     __("
    -0.06
    \<^
    -0.06
    Hang
    -0.06
     spokesman
    -0.06
    POSITIVE LOGITS
     everything
    0.07
    iene
    0.07
    imon
    0.06
     space
    0.06
    ollider
    0.06
    ulu
    0.06
    oot
    0.06
     moments
    0.06
    AndView
    0.06
    202
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.