© 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. 118739
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions, particularly high schools

    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
    hind
    -0.08
    ushman
    -0.08
    oyer
    -0.07
    ieber
    -0.07
    ilyn
    -0.07
    idth
    -0.07
    еÑĢв
    -0.07
    ÑĭÑĤ
    -0.07
    dur
    -0.07
    ervo
    -0.07
    POSITIVE LOGITS
    985
    0.06
     ÑĢазви
    0.06
    owment
    0.06
    aku
    0.06
    357
    0.06
    atos
    0.06
     Jarvis
    0.05
    uten
    0.05
    rog
    0.05
    442
    0.05
    Activations Density 0.009%

    No Known Activations