© 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. 95820
    Prev
    Next
    INDEX
    Explanations

    phrases related to behavioral issues and discipline in educational contexts

    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
    avl
    -0.07
     pap
    -0.07
    çŃĴ
    -0.07
     Kramer
    -0.06
     traps
    -0.06
    trap
    -0.06
    fault
    -0.06
    iller
    -0.06
    illez
    -0.06
    oller
    -0.06
    POSITIVE LOGITS
     Suspension
    0.10
     suspension
    0.09
     susp
    0.08
    suspend
    0.08
     disciplinary
    0.07
    ÑĥÑĩа
    0.07
     Violence
    0.07
     suspend
    0.07
    heck
    0.07
    zilla
    0.07
    Activations Density 0.003%

    No Known Activations