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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106101
    Prev
    Next
    INDEX
    Explanations

    references to military leadership and battles

    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
    istrovstvÃŃ
    -0.10
     personel
    -0.08
    rosso
    -0.08
     poil
    -0.08
     mastur
    -0.07
    ection
    -0.07
    /internal
    -0.07
    оÑĤÑĢеб
    -0.07
    indows
    -0.07
    amer
    -0.07
    POSITIVE LOGITS
     camping
    0.06
     tráºŃn
    0.06
    panic
    0.06
     circ
    0.06
     Sizes
    0.05
    ahu
    0.05
     compositions
    0.05
     Holmes
    0.05
     Aging
    0.05
     bottleneck
    0.05
    Activations Density 0.017%

    No Known Activations