© 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. 61477
    Prev
    Next
    INDEX
    Explanations

    references to exclusive rights and licenses

    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
    lok
    -0.08
    onya
    -0.08
    esch
    -0.07
    ilde
    -0.07
    editary
    -0.07
    ÑĩаÑģ
    -0.07
    usk
    -0.07
    acer
    -0.07
    cribe
    -0.07
    èm
    -0.07
    POSITIVE LOGITS
    -purpose
    0.09
    ively
    0.08
    /un
    0.08
    iveness
    0.07
    ities
    0.07
    izard
    0.07
    idad
    0.07
     olarak
    0.07
    /private
    0.07
    ELY
    0.07
    Activations Density 0.008%

    No Known Activations