© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80861
    Prev
    Next
    INDEX
    Explanations

    academic titles and positions within the context of a prestigious announcement or publication

    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
     assistant
    -0.10
     Assistant
    -0.10
    Assistant
    -0.10
    assistant
    -0.09
     assistants
    -0.08
     Licensed
    -0.08
    emain
    -0.07
    @student
    -0.07
    icut
    -0.07
    ãĥ¼ãĥ³
    -0.07
    POSITIVE LOGITS
     professor
    0.10
     Professor
    0.09
     prof
    0.09
    Professor
    0.08
     Prof
    0.08
     professors
    0.08
    æķĻæİĪ
    0.07
    prof
    0.07
     dean
    0.06
     profil
    0.06
    Activations Density 0.045%

    No Known Activations