© 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. 97727
    Prev
    Next
    INDEX
    Explanations

    terms related to execution and process management

    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
    agem
    -0.07
    voor
    -0.07
    /all
    -0.07
    öst
    -0.07
    ishment
    -0.07
    asso
    -0.07
    ungan
    -0.07
    /mac
    -0.07
    ong
    -0.07
     McMahon
    -0.07
    POSITIVE LOGITS
    anter
    0.09
    isable
    0.07
     eslint
    0.07
    /render
    0.07
    UTION
    0.07
    aneous
    0.06
    ãĥ¼ãĥ
    0.06
    erg
    0.06
    ĩ
    0.06
    prising
    0.06
    Activations Density 0.021%

    No Known Activations