© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 83345
    Prev
    Next
    INDEX
    Explanations

    mentions of jails and correctional 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
    ajor
    -0.06
    ousse
    -0.06
    âĢ¡
    -0.06
     graph
    -0.05
     institutes
    -0.05
    rist
    -0.05
     Masters
    -0.05
     trick
    -0.05
     pit
    -0.05
     pits
    -0.05
    POSITIVE LOGITS
    ADX
    0.08
     DISCLAIM
    0.08
    utenberg
    0.08
    velt
    0.08
    etler
    0.07
    ebra
    0.07
    sov
    0.07
    zik
    0.07
    umber
    0.07
    constructor
    0.07
    Activations Density 0.000%

    No Known Activations