© 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 EvalsExportsAPI 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. 87281
    Prev
    Next
    INDEX
    Explanations

    references to staff members and their roles in educational settings

    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
     regional
    -0.07
    friends
    -0.06
    aju
    -0.06
     preco
    -0.06
    plates
    -0.06
    ombine
    -0.06
    ë¨
    -0.06
     stri
    -0.06
    .Undef
    -0.06
    skyt
    -0.05
    POSITIVE LOGITS
    åħĪçĶŁ
    0.08
    æķĻ
    0.08
     teacher
    0.07
     Mrs
    0.07
     Coach
    0.07
     teaching
    0.07
    èĢģå¸Ī
    0.07
    Mrs
    0.07
     teachers
    0.07
     Teacher
    0.07
    Activations Density 0.090%

    No Known Activations