© 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. 55079
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating the concept of existence or identity

    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
    clist
    -0.07
    ugin
    -0.07
    ocha
    -0.07
    vn
    -0.06
    aos
    -0.06
    /open
    -0.06
     onun
    -0.06
    onas
    -0.06
    etine
    -0.06
    _RAM
    -0.06
    POSITIVE LOGITS
     there
    0.14
    there
    0.11
     There
    0.09
     certain
    0.08
     THERE
    0.08
     things
    0.08
    There
    0.08
    Certain
    0.08
     Certain
    0.07
     we
    0.07
    Activations Density 0.005%

    No Known Activations