© 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. 85507
    Prev
    Next
    INDEX
    Explanations

    references to missing persons and their investigations

    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
    heritance
    -0.07
    ystore
    -0.07
    é»
    -0.07
    okol
    -0.07
    vox
    -0.07
    illions
    -0.07
    æ»ħ
    -0.07
     Hlav
    -0.07
    ddy
    -0.07
    yal
    -0.07
    POSITIVE LOGITS
     wanted
    0.08
     extrad
    0.07
     Wanted
    0.07
     Eu
    0.07
     fug
    0.06
    wanted
    0.06
     actively
    0.06
     ev
    0.06
     appreh
    0.06
    ushima
    0.06
    Activations Density 0.003%

    No Known Activations