© 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. 88103
    Prev
    Next
    INDEX
    Explanations

    specific legal citations and references within case law

    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
    ymce
    -0.07
    ÄĻ
    -0.07
    abis
    -0.06
    croft
    -0.06
    chet
    -0.06
    itz
    -0.06
    ORIZONTAL
    -0.06
    addtogroup
    -0.06
    irus
    -0.06
    enda
    -0.06
    POSITIVE LOGITS
    //{{
    0.06
    £¼
    0.06
    "]->
    0.06
    ħ§
    0.06
    ansas
    0.06
     Äijá»Ļng
    0.06
    ़
    0.06
    ãĥ³ãĤ¿
    0.06
     Mystic
    0.06
     vib
    0.05
    Activations Density 0.003%

    No Known Activations