© 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. 15-LLAMASCOPE-RES-131K
    11. 88645
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "com" related to code or package imports

    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
    åı
    -0.07
    utherford
    -0.07
    onz
    -0.07
    afen
    -0.06
    лÑĥ
    -0.06
    isc
    -0.06
    lich
    -0.06
    .uk
    -0.06
     Kob
    -0.06
    istinguish
    -0.06
    POSITIVE LOGITS
    ersist
    0.07
    qrst
    0.07
    ForeColor
    0.07
    ãĥĨãĥ«
    0.06
    IDEOS
    0.06
    ,'#
    0.06
    Âłmiles
    0.06
    ìŀIJìĿ¸
    0.06
    inant
    0.06
    kad
    0.06
    Activations Density 0.001%

    No Known Activations