© 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. 94376
    Prev
    Next
    INDEX
    Explanations

    references to international agreements and partnerships

    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
     Playboy
    -0.07
    rcode
    -0.07
    anki
    -0.07
    jug
    -0.06
    rix
    -0.06
    ãĥ¼ãĥ³
    -0.06
    "+"
    -0.06
    iddy
    -0.06
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.06
    ủi
    -0.06
    POSITIVE LOGITS
     Pratt
    0.07
    IPC
    0.06
    .metro
    0.06
    437
    0.06
    ardo
    0.06
    é½IJ
    0.06
    ÐķС
    0.06
    ingt
    0.06
     Shot
    0.06
     Schmidt
    0.06
    Activations Density 0.001%

    No Known Activations