© 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. 88479
    Prev
    Next
    INDEX
    Explanations

    boolean values and related programming keywords

    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
    elts
    -0.07
     McMahon
    -0.07
    zcze
    -0.07
    ffen
    -0.06
    íĺ¸
    -0.06
    iddle
    -0.06
    balances
    -0.06
    agma
    -0.06
    iferay
    -0.06
     Caldwell
    -0.06
    POSITIVE LOGITS
    ief
    0.07
    imos
    0.07
    onal
    0.07
    ØŃاد
    0.07
    amber
    0.06
    odom
    0.06
     ä¸
    0.06
    æĹĹ
    0.06
    adh
    0.06
    (disposing
    0.06
    Activations Density 0.000%

    No Known Activations