© 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. 118333
    Prev
    Next
    INDEX
    Explanations

    instances of scores, statistics, or game progress in sports contexts

    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
     Ecc
    -0.07
     ac
    -0.06
    pton
    -0.06
    å¼ı
    -0.06
    OKIE
    -0.06
    OSE
    -0.06
     PR
    -0.06
    assel
    -0.05
    okie
    -0.05
     transit
    -0.05
    POSITIVE LOGITS
     départ
    0.08
    overn
    0.07
    thanks
    0.07
     thanks
    0.07
    angu
    0.07
    olley
    0.07
    zi
    0.07
    ãĥ³ãĥĨ
    0.07
    xp
    0.07
     æĹ
    0.07
    Activations Density 0.011%

    No Known Activations