© 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. 107119
    Prev
    Next
    INDEX
    Explanations

    elements related to system features and functionalities

    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
    -widgets
    -0.08
    ê±°ëŀĺê°Ģ
    -0.07
    _ENCODING
    -0.07
    ensely
    -0.06
    надлеж
    -0.06
    angers
    -0.06
    ownt
    -0.06
     اÙĤ
    -0.06
    Neutral
    -0.06
    erli
    -0.06
    POSITIVE LOGITS
    aska
    0.06
    ãĤ¶ãĥ¼
    0.06
    astr
    0.06
    ика
    0.06
    htar
    0.06
    flix
    0.06
    raz
    0.06
    edit
    0.06
    éĮ
    0.06
     freely
    0.06
    Activations Density 0.001%

    No Known Activations