© 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. 87870
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and constructs

    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
    antro
    -0.07
    rolled
    -0.07
    çĬ¬
    -0.07
    ilingual
    -0.07
    nock
    -0.07
    ÑĥлÑİ
    -0.06
    uld
    -0.06
    :\/\/
    -0.06
    iesen
    -0.06
    amer
    -0.06
    POSITIVE LOGITS
    :↵
    0.08
    :
    0.07
    ãĥĥãĤ«ãĥ¼
    0.06
    å¦Ĥä¸ĭ
    0.06
    LOT
    0.06
    *:
    0.06
    Map
    0.06
     rim
    0.06
     pres
    0.06
    :↵↵
    0.06
    Activations Density 0.040%

    No Known Activations