© 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. 118748
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement and legal processes

    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
    orden
    -0.07
    hod
    -0.06
    amo
    -0.06
    ĬìĿĢ
    -0.06
    LÄ°
    -0.06
    ãĥ¼ãĥŀ
    -0.05
    Trivia
    -0.05
    inc
    -0.05
    KD
    -0.05
     Airways
    -0.05
    POSITIVE LOGITS
    rig
    0.07
    ModelProperty
    0.07
    lán
    0.07
    鹿
    0.07
    kyt
    0.07
    Cancelable
    0.06
    ihu
    0.06
    /*@
    0.06
    .Assembly
    0.06
    алÑĥ
    0.06
    Activations Density 0.008%

    No Known Activations