© 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. 118233
    Prev
    Next
    INDEX
    Explanations

    names of journalists and contributors in news contexts

    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
    itarian
    -0.07
    781
    -0.06
    anness
    -0.06
    978
    -0.06
    quared
    -0.06
    trap
    -0.05
    (Unknown
    -0.05
    stakes
    -0.05
     ped
    -0.05
     fame
    -0.05
    POSITIVE LOGITS
     reporting
    0.10
    Reporting
    0.09
     Reporting
    0.08
    æĬ¥éģĵ
    0.08
     reported
    0.08
    reports
    0.08
     reporters
    0.08
    ække
    0.07
     reports
    0.07
     reporter
    0.07
    Activations Density 0.097%

    No Known Activations