© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 75545
    Prev
    Next
    INDEX
    Explanations

    concepts related to machine learning and video prediction technologies

    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
     Exercise
    -0.07
    Exercise
    -0.07
    ktop
    -0.07
    exercise
    -0.06
     exercise
    -0.06
    agina
    -0.06
    wich
    -0.06
     fil
    -0.06
    itre
    -0.06
     sna
    -0.06
    POSITIVE LOGITS
     Safety
    0.07
    Safety
    0.07
    utsch
    0.07
     ë°°ìļ°
    0.06
     safety
    0.06
    æĦŁ
    0.06
    Runtime
    0.06
    _navigation
    0.06
    ût
    0.06
     Runtime
    0.06
    Activations Density 0.008%

    No Known Activations