© 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. 39698
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions and documentation

    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
    mamak
    -0.06
    ais
    -0.06
    asta
    -0.06
    conto
    -0.06
    istrov
    -0.06
    .mixin
    -0.06
    ffen
    -0.05
    ix
    -0.05
    roje
    -0.05
    isl
    -0.05
    POSITIVE LOGITS
     Dunn
    0.08
    lr
    0.07
    ifest
    0.07
    /ion
    0.06
     Hire
    0.06
     cest
    0.06
    quential
    0.06
    ůl
    0.06
    icker
    0.06
    éĴŁ
    0.06
    Activations Density 0.000%

    No Known Activations