© 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. 2271
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of awareness or uncertainty about future events

    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
     known
    -0.06
    retty
    -0.06
    995
    -0.06
    opsy
    -0.06
    nah
    -0.06
     likely
    -0.06
     claro
    -0.06
    inar
    -0.06
    ût
    -0.06
     phenomenon
    -0.06
    POSITIVE LOGITS
     nor
    0.09
    _submenu
    0.08
     anymore
    0.07
     or
    0.07
    ή
    0.07
     или
    0.07
     tomorrow
    0.07
     Norris
    0.07
    might
    0.07
    CESS
    0.06
    Activations Density 0.015%

    No Known Activations