© 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. 126702
    Prev
    Next
    INDEX
    Explanations

    references to expressions of condolence and memorial gestures

    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
    159
    -0.07
     deb
    -0.07
    ãĥ©ãĤ¹
    -0.07
     />'
    -0.07
    haus
    -0.06
    .backup
    -0.06
     Clay
    -0.06
     æ¿
    -0.06
    ount
    -0.06
    519
    -0.06
    POSITIVE LOGITS
     please
    0.07
    ltk
    0.06
    please
    0.06
    ase
    0.06
    anity
    0.06
    idity
    0.06
    ulence
    0.06
     Miy
    0.06
     Saul
    0.06
    WebpackPlugin
    0.05
    Activations Density 0.000%

    No Known Activations