© 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. 95948
    Prev
    Next
    INDEX
    Explanations

    references to academic positions and roles, particularly related to teaching and professorships

    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
    ahlen
    -0.07
    Ä©
    -0.07
    ufen
    -0.07
    ÃŃk
    -0.06
    NIC
    -0.06
    Tween
    -0.06
    eci
    -0.06
    боÑĤ
    -0.06
    omic
    -0.06
    гов
    -0.06
    POSITIVE LOGITS
     teaching
    0.13
     teach
    0.11
     teachings
    0.11
     teaches
    0.10
     taught
    0.10
     lect
    0.10
    æķĻ
    0.09
    æİĪ
    0.09
     classes
    0.09
     Teaching
    0.08
    Activations Density 0.052%

    No Known Activations