© 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 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. 29246
    Prev
    Next
    INDEX
    Explanations

    aspects related to measurement and quantity

    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
    ousel
    -0.08
    resh
    -0.07
    ilor
    -0.07
    uer
    -0.06
    ropoda
    -0.06
    ói
    -0.06
    _Entry
    -0.06
     dri
    -0.06
    ichi
    -0.06
     cin
    -0.06
    POSITIVE LOGITS
    ÑģÑĮ
    0.07
    Excel
    0.06
    innen
    0.06
     Nurs
    0.06
     Excel
    0.06
    ÑģÑı
    0.06
    anter
    0.06
    eland
    0.06
    >{!!
    0.06
     Koh
    0.06
    Activations Density 0.003%

    No Known Activations