© 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. 2016
    Prev
    Next
    INDEX
    Explanations

    phrases related to proposals and job applications

    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
    aroo
    -0.09
    alars
    -0.08
    ONTAL
    -0.08
    aram
    -0.08
    érique
    -0.07
    olis
    -0.07
    AndGet
    -0.07
    اراÙĨ
    -0.07
    vla
    -0.07
    uien
    -0.07
    POSITIVE LOGITS
     Morrison
    0.06
    _hooks
    0.06
     Burke
    0.06
    ç¸
    0.06
    acket
    0.05
    0.05
     prior
    0.05
    ÑĦик
    0.05
     present
    0.05
     hitch
    0.05
    Activations Density 0.012%

    No Known Activations