© 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. 27519
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating a pause or separation in text

    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
    ritch
    -0.09
    LEAN
    -0.08
    ILER
    -0.08
    .Companion
    -0.08
    бÑĥдÑĮ
    -0.08
    LOUR
    -0.08
    лоп
    -0.07
    elps
    -0.07
    ampoo
    -0.07
    olang
    -0.07
    POSITIVE LOGITS
    lei
    0.06
     K
    0.06
     majority
    0.05
     intoxic
    0.05
     NV
    0.05
    0.05
     McGu
    0.05
     multitude
    0.05
     until
    0.05
     prefix
    0.05
    Activations Density 0.000%

    No Known Activations