© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82220
    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
    ksam
    -0.09
    readcr
    -0.08
    cean
    -0.08
    intage
    -0.08
    598
    -0.08
    iesel
    -0.08
    sez
    -0.07
    ntag
    -0.07
    utar
    -0.07
    ávÄĽ
    -0.07
    POSITIVE LOGITS
     qu
    0.07
     pur
    0.07
     detox
    0.06
     abst
    0.06
    435
    0.06
    708
    0.06
     White
    0.06
    orden
    0.06
    .uid
    0.05
     op
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.