© 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. 15603
    Prev
    Next
    INDEX
    Explanations

    references to cultural and historical changes

    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
    arto
    -0.06
    ismet
    -0.06
    ož
    -0.06
    ÑģÑĤвенно
    -0.06
    /about
    -0.06
    Ð
    -0.06
    enco
    -0.06
    celik
    -0.06
    æŶåĢĻ
    -0.06
    /to
    -0.06
    POSITIVE LOGITS
     la
    0.09
    lah
    0.09
    lej
    0.08
    la
    0.07
    theid
    0.07
    ÏĦαι
    0.07
     loa
    0.06
    asca
    0.06
    -La
    0.06
     Pla
    0.06
    Activations Density 0.047%

    No Known Activations