© 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. 97647
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "neutrino."

    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
    Ø©
    -0.07
    obar
    -0.07
    ipelines
    -0.07
    obe
    -0.07
    thag
    -0.07
    elah
    -0.07
    oe
    -0.06
    apiro
    -0.06
    adero
    -0.06
    eni
    -0.06
    POSITIVE LOGITS
    sher
    0.07
    sak
    0.07
    lor
    0.07
    üven
    0.06
    wnd
    0.06
    ì²ľ
    0.06
     sơ
    0.06
     invent
    0.06
    s
    0.06
     propTypes
    0.05
    Activations Density 0.002%

    No Known Activations