© 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. 62841
    Prev
    Next
    INDEX
    Explanations

    various forms of the article "the" and pronouns indicating possessiveness or quantity

    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
    imers
    -0.07
    ë¶ģ
    -0.07
    .WinForms
    -0.07
    ifers
    -0.07
    ussen
    -0.07
    getReference
    -0.07
    abbo
    -0.07
     åĥ
    -0.07
    ÑĦа
    -0.07
    :def
    -0.07
    POSITIVE LOGITS
     questions
    0.09
     question
    0.08
     permission
    0.07
     rhet
    0.07
     for
    0.07
    ew
    0.07
     Questions
    0.07
     forgiveness
    0.07
     audience
    0.06
     audiences
    0.06
    Activations Density 0.010%

    No Known Activations