© 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. 17-LLAMASCOPE-RES-131K
    11. 83554
    Prev
    Next
    INDEX
    Explanations

    discussions around definitions and classifications of animals and food items

    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
    ableView
    -0.06
    pais
    -0.06
    lder
    -0.06
    dub
    -0.06
    etat
    -0.06
    umo
    -0.06
    ucid
    -0.06
    phis
    -0.06
    311
    -0.06
    lope
    -0.06
    POSITIVE LOGITS
    635
    0.07
    yı
    0.07
    iete
    0.07
    yled
    0.07
    pite
    0.07
    åĿļ
    0.06
    techn
    0.06
     kin
    0.06
     práv
    0.06
     actually
    0.06
    Activations Density 0.009%

    No Known Activations