© 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. 73217
    Prev
    Next
    INDEX
    Explanations

    references to educational materials and worksheets

    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
     POV
    -0.06
     natural
    -0.06
     Natural
    -0.05
    pressor
    -0.05
     RENDER
    -0.05
     Lux
    -0.05
     critical
    -0.05
     Gloss
    -0.05
     restricted
    -0.05
    ReactDOM
    -0.05
    POSITIVE LOGITS
    Teacher
    0.08
     Teacher
    0.08
    Tp
    0.08
     Teachers
    0.08
    anness
    0.08
    teachers
    0.07
    UGHT
    0.07
    teacher
    0.07
     Teaching
    0.07
     teacher
    0.07
    Activations Density 0.008%

    No Known Activations