© 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. 29301
    Prev
    Next
    INDEX
    Explanations

    references to various World Wars and their events

    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
    akin
    -0.07
    ikan
    -0.07
    erva
    -0.06
    egie
    -0.06
     whe
    -0.06
    IPHER
    -0.06
    EI
    -0.06
    erç
    -0.06
    wit
    -0.06
     Hond
    -0.06
    POSITIVE LOGITS
    ington
    0.08
    áo
    0.07
    UED
    0.07
    lord
    0.07
    inded
    0.06
    æ£ļ
    0.06
    blers
    0.06
    inding
    0.06
    iness
    0.06
    mmc
    0.06
    Activations Density 0.005%

    No Known Activations