© 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. 117954
    Prev
    Next
    INDEX
    Explanations

    references to training and education related to safety and support, particularly in a school or organizational context

    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
    боÑĤ
    -0.07
     Carn
    -0.07
    oyo
    -0.07
    enschaft
    -0.07
    chter
    -0.06
     admissions
    -0.06
    Indexed
    -0.06
    ekk
    -0.06
     Admission
    -0.06
    æ¦ľ
    -0.06
    POSITIVE LOGITS
     training
    0.20
    training
    0.17
     Training
    0.17
    -training
    0.16
    Training
    0.15
    _training
    0.13
     TRAIN
    0.13
     train
    0.13
     trainers
    0.12
     trainer
    0.12
    Activations Density 0.068%

    No Known Activations