© 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. 9-LLAMASCOPE-RES-131K
    11. 98161
    Prev
    Next
    INDEX
    Explanations

    the word "About" in varying 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
     Pros
    -0.06
    S
    -0.06
     ModelState
    -0.06
    enty
    -0.06
    ught
    -0.06
    esso
    -0.06
    innen
    -0.05
    abra
    -0.05
     Zend
    -0.05
     posix
    -0.05
    POSITIVE LOGITS
    chwitz
    0.08
    ohl
    0.08
    .grp
    0.08
    hwnd
    0.08
    subtype
    0.07
    umont
    0.07
    gratis
    0.07
    Derived
    0.07
    #!
    0.07
    LOPT
    0.07
    Activations Density 0.007%

    No Known Activations