© 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. 58078
    Prev
    Next
    INDEX
    Explanations

    references to significant events and individuals related to journalism

    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
    erp
    -0.07
     thrott
    -0.07
    wang
    -0.06
    lam
    -0.06
    uent
    -0.06
    wolf
    -0.06
     Weiner
    -0.06
    æ²³
    -0.06
    alar
    -0.06
    iram
    -0.06
    POSITIVE LOGITS
     Caribbean
    0.10
     Trinidad
    0.09
     Barb
    0.09
    igua
    0.09
     SVG
    0.09
     Guy
    0.08
    Guy
    0.08
     island
    0.08
     Gren
    0.08
     NOTICE
    0.08
    Activations Density 0.079%

    No Known Activations