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

    Neuronpedia

    Jacobian LensNEW
    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. 128918
    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
    wart
    -0.07
    ole
    -0.06
    Dear
    -0.06
    alcon
    -0.06
    oles
    -0.06
    bam
    -0.06
     Dear
    -0.06
     Wort
    -0.05
     sá»ijng
    -0.05
    571
    -0.05
    POSITIVE LOGITS
     skl
    0.08
    ình
    0.08
    .truth
    0.07
    rij
    0.07
    ick
    0.07
    lá
    0.07
    .Factory
    0.07
     Trilogy
    0.07
    åľ
    0.06
    uffix
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.