© 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. 75025
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or hypothetical scenarios

    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
    igest
    -0.06
    ãĤĵ
    -0.06
     registers
    -0.06
    range
    -0.06
    -ci
    -0.06
     quis
    -0.06
     grav
    -0.06
    ael
    -0.06
    ativ
    -0.05
     Armour
    -0.05
    POSITIVE LOGITS
    ÑĹ
    0.06
     BTN
    0.06
    ìĪł
    0.06
    ARRIER
    0.06
     nutshell
    0.06
    (æ°´
    0.06
    .bam
    0.06
    ç¥
    0.06
    Sizer
    0.06
    inea
    0.06
    Activations Density 0.003%

    No Known Activations