© 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. 82872
    Prev
    Next
    INDEX
    Explanations

    legislative actions and designations related to postal service facilities

    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
    atan
    -0.07
    GLOBALS
    -0.06
    rew
    -0.06
     YYS
    -0.06
    lock
    -0.06
    osl
    -0.06
    lasses
    -0.06
     Meyer
    -0.06
    ILLE
    -0.05
     version
    -0.05
    POSITIVE LOGITS
    ãİ
    0.07
    ãĥ¼ãĥį
    0.07
    getVar
    0.07
    _install
    0.07
    _IOC
    0.07
     poil
    0.07
    /Delete
    0.07
    ooke
    0.07
    Installer
    0.07
     знов
    0.06
    Activations Density 0.029%

    No Known Activations