© 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. 84929
    Prev
    Next
    INDEX
    Explanations

    numeric codes or values related to dates and statistics

    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
     squ
    -0.06
     situ
    -0.06
    apore
    -0.06
    orrent
    -0.06
    bia
    -0.06
    uem
    -0.05
     paraph
    -0.05
     allem
    -0.05
    loff
    -0.05
    inform
    -0.05
    POSITIVE LOGITS
    SENS
    0.07
     Angiospermae
    0.07
    (æľĪ
    0.07
    æģ¯
    0.07
    ICAST
    0.07
    abee
    0.07
    abox
    0.07
    pit
    0.07
    ¶Į
    0.07
     pit
    0.07
    Activations Density 0.005%

    No Known Activations