© 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. 104441
    Prev
    Next
    INDEX
    Explanations

    references to the origins or sources of materials and products

    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
    avel
    -0.08
    Ø°Ùĥر
    -0.07
    yd
    -0.07
    íijľ
    -0.06
    ERM
    -0.06
    воÑİ
    -0.06
    ()>↵
    -0.06
    ftware
    -0.06
    .IsEmpty
    -0.06
    atron
    -0.06
    POSITIVE LOGITS
    oplast
    0.07
    eyse
    0.07
    ears
    0.06
    /to
    0.06
     nowhere
    0.06
    amoto
    0.06
    resi
    0.06
    late
    0.06
    isÃŃ
    0.05
    compat
    0.05
    Activations Density 0.039%

    No Known Activations