© 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. 59782
    Prev
    Next
    INDEX
    Explanations

    information related to ticket purchasing and event details

    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
     therefore
    -0.07
    495
    -0.06
    oks
    -0.06
     Staples
    -0.06
     indeed
    -0.06
    849
    -0.06
    owing
    -0.06
     Lead
    -0.06
     prim
    -0.06
    Ñħи
    -0.06
    POSITIVE LOGITS
    Alternatively
    0.12
     Alternatively
    0.12
    або
    0.08
     alternatively
    0.08
     Altern
    0.07
    alternative
    0.07
     alternative
    0.07
    Altern
    0.07
     Alternative
    0.07
    orp
    0.07
    Activations Density 0.029%

    No Known Activations