© 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. 41301
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and their importance in the context of health and sexuality

    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
    599
    -0.07
    dropout
    -0.06
     Buff
    -0.06
     Py
    -0.06
     Pod
    -0.06
    451
    -0.06
    564
    -0.06
    vailability
    -0.06
     Bik
    -0.06
    vor
    -0.05
    POSITIVE LOGITS
    onas
    0.07
    ımızı
    0.07
    ımıza
    0.07
    adal
    0.07
    atto
    0.07
    öm
    0.07
    jni
    0.07
    clr
    0.07
    ÙĦÙĪ
    0.07
    rava
    0.07
    Activations Density 0.000%

    No Known Activations