© 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. 130712
    Prev
    Next
    INDEX
    Explanations

    references to mermaids and related themes

    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
     dinosaurs
    -0.07
    ycz
    -0.07
     FileAccess
    -0.06
    apot
    -0.06
     Sob
    -0.06
     snakes
    -0.06
    ekler
    -0.06
    èģĶ
    -0.06
    acket
    -0.06
    abis
    -0.06
    POSITIVE LOGITS
     Ariel
    0.08
     prince
    0.08
     fish
    0.07
     Prince
    0.07
     fins
    0.06
     bott
    0.06
     Fish
    0.06
    ТÐŀ
    0.06
    lio
    0.06
    Prince
    0.06
    Activations Density 0.003%

    No Known Activations