© 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. 130089
    Prev
    Next
    INDEX
    Explanations

    statistical representations and graphical elements in data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    .variables
    -0.07
     MATRIX
    -0.06
     imageSize
    -0.06
    =$((
    -0.06
     confirmPassword
    -0.06
    essler
    -0.06
    ιαν
    -0.06
    ymous
    -0.06
    Table
    -0.06
    wit
    -0.06
    POSITIVE LOGITS
     curve
    0.10
     curves
    0.08
     Curve
    0.07
    urve
    0.07
     points
    0.07
    Curve
    0.07
    rawer
    0.07
     BLUE
    0.07
     line
    0.07
     graph
    0.07
    Activations Density 0.083%

    No Known Activations