© 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. 78528
    Prev
    Next
    INDEX
    Explanations

    names and references related to individuals

    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
    maid
    -0.08
    olut
    -0.07
    f
    -0.07
    nger
    -0.07
    fy
    -0.07
    ous
    -0.07
    maal
    -0.07
    kker
    -0.07
    ways
    -0.06
     Platt
    -0.06
    POSITIVE LOGITS
    uvre
    0.10
    oe
    0.07
    itsu
    0.07
    ç´ł
    0.07
    bling
    0.07
    bean
    0.07
    portun
    0.06
    ajas
    0.06
    lectric
    0.06
    regor
    0.06
    Activations Density 0.016%

    No Known Activations