© 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. 86922
    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
     –
    -0.07
    eli
    -0.07
    obe
    -0.06
    enburg
    -0.06
     i
    -0.06
    566
    -0.06
     -
    -0.06
     â
    -0.06
     saw
    -0.05
     Folk
    -0.05
    POSITIVE LOGITS
    anes
    0.07
     ``(
    0.07
    ikip
    0.07
    iÄįe
    0.07
    ãĥ¼ãĥĩ
    0.07
    igt
    0.07
    wap
    0.07
    воз
    0.07
    bone
    0.07
    еко
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.