© 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 EvalsExportsinterp-engineNEWAPI 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. 69908
    Prev
    Next
    INDEX
    Explanations

    phrases that convey uncertainty or the perception of strangeness

    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
     Trot
    -0.07
    ój
    -0.06
     Verfügung
    -0.06
    hora
    -0.06
     Sommer
    -0.06
    illet
    -0.06
    enberg
    -0.06
    оÑĢм
    -0.06
    iever
    -0.05
    linkplain
    -0.05
    POSITIVE LOGITS
     зда
    0.07
    OKIE
    0.07
    ableView
    0.07
    .asList
    0.07
    CHANT
    0.06
    achs
    0.06
    Periph
    0.06
    ÙĬب
    0.06
    º«
    0.06
     عص
    0.06
    Activations Density 0.011%

    No Known Activations