© 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 EvalsExportsAPI 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. 126507
    Prev
    Next
    INDEX
    Explanations

    terms related to disruption and disruptive change

    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
    ause
    -0.08
    enu
    -0.08
    عÙħ
    -0.07
    รà¸Ķ
    -0.07
    borg
    -0.07
    ettle
    -0.07
    atura
    -0.07
    ows
    -0.07
    ervo
    -0.07
    wick
    -0.07
    POSITIVE LOGITS
    ively
    0.10
    ive
    0.07
    antly
    0.07
    857
    0.07
    ingly
    0.07
    iveness
    0.07
    ois
    0.07
    /conf
    0.07
    /dist
    0.07
    /dis
    0.07
    Activations Density 0.008%

    No Known Activations