© 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. 29208
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax elements

    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
    OrDefault
    -0.06
    igned
    -0.06
    pac
    -0.06
    BU
    -0.06
     pot
    -0.05
    çŃĨ
    -0.05
    wpdb
    -0.05
     Ger
    -0.05
    pour
    -0.05
     Beck
    -0.05
    POSITIVE LOGITS
    Insensitive
    0.07
    PropertyDescriptor
    0.07
    ÑĢиз
    0.07
    iji
    0.07
    alia
    0.07
    OrNil
    0.06
    StringEncoding
    0.06
    .cg
    0.06
    WithDuration
    0.06
    elpers
    0.06
    Activations Density 0.002%

    No Known Activations