© 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. 60380
    Prev
    Next
    INDEX
    Explanations

    technical terms and references to action

    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
     Daly
    -0.06
    inux
    -0.06
     discrim
    -0.06
     discrimin
    -0.06
    izar
    -0.06
     occupancy
    -0.06
     Relief
    -0.06
    izz
    -0.06
    .TypeOf
    -0.05
    978
    -0.05
    POSITIVE LOGITS
    steder
    0.08
    usercontent
    0.08
    Tube
    0.08
    egov
    0.07
    ÅĻÃŃd
    0.07
    tube
    0.07
    ifact
    0.07
    aleigh
    0.07
    Ùĩر
    0.07
    Tier
    0.06
    Activations Density 0.001%

    No Known Activations