© 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. 93017
    Prev
    Next
    INDEX
    Explanations

    names of individuals or references related to specific people

    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
    osg
    -0.08
    inki
    -0.08
    asInstanceOf
    -0.08
    ridor
    -0.08
    antor
    -0.08
    addock
    -0.07
    имÑĥ
    -0.07
    krv
    -0.07
    Ñĸж
    -0.07
    GGLE
    -0.07
    POSITIVE LOGITS
     Brian
    0.06
    ani
    0.05
    337
    0.05
    baugh
    0.05
    .liferay
    0.05
     stud
    0.05
    ano
    0.05
     economically
    0.05
    Id
    0.05
    -root
    0.05
    Activations Density 0.001%

    No Known Activations