© 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. 15-LLAMASCOPE-RES-131K
    11. 88902
    Prev
    Next
    INDEX
    Explanations

    references to academic citations or supporting literature

    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
    osal
    -0.07
    ICES
    -0.07
    otas
    -0.06
    idon
    -0.06
    ottie
    -0.06
    ãģķãģĽ
    -0.06
    getRepository
    -0.06
    .yml
    -0.06
    amas
    -0.06
    TL
    -0.06
    POSITIVE LOGITS
    arness
    0.07
    sons
    0.07
     ÑĨÑı
    0.06
     Schwarz
    0.06
     lately
    0.06
    nemonic
    0.06
    @nate
    0.06
    .validators
    0.06
    ädchen
    0.06
    ruh
    0.06
    Activations Density 0.010%

    No Known Activations