© 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 EvalsExportsinterp-engineNEWAPI 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. 79672
    Prev
    Next
    INDEX
    Explanations

    phrases that promote engagement and encourage action

    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
    ãĢħ
    -0.07
    lose
    -0.07
    ikes
    -0.06
     Ferguson
    -0.06
     Lowest
    -0.06
     Nguyên
    -0.06
     Goldberg
    -0.06
    ATIVE
    -0.06
     replication
    -0.05
    urar
    -0.05
    POSITIVE LOGITS
    MLS
    0.08
    luž
    0.07
     Parcel
    0.07
     Leaf
    0.07
    iet
    0.07
    chy
    0.06
    armed
    0.06
    .instant
    0.06
    lyn
    0.06
    WithData
    0.06
    Activations Density 0.002%

    No Known Activations