© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 71194
    Prev
    Next
    INDEX
    Explanations

    phrases indicating risk or caution in sports contexts

    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
    entic
    -0.08
    adiens
    -0.07
    rance
    -0.07
    .yahoo
    -0.07
    нед
    -0.07
    ention
    -0.06
    åĬĥ
    -0.06
    thur
    -0.06
     fond
    -0.06
    /cop
    -0.06
    POSITIVE LOGITS
    OnError
    0.07
     Mo
    0.07
    ifo
    0.06
    .mo
    0.06
    isol
    0.06
     McL
    0.06
     fucks
    0.05
    idar
    0.05
     mo
    0.05
    omics
    0.05
    Activations Density 0.000%

    No Known Activations