© 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. 60385
    Prev
    Next
    INDEX
    Explanations

    references to aircraft and their operations

    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
    ady
    -0.07
     kelim
    -0.07
    monkey
    -0.07
    äºŃ
    -0.07
     ucwords
    -0.07
    ادÙĦ
    -0.06
    gren
    -0.06
    vais
    -0.06
    aines
    -0.06
    ÏĢÎŃ
    -0.06
    POSITIVE LOGITS
     craft
    0.07
    855
    0.06
    å°¾
    0.06
     noise
    0.06
     watchers
    0.06
     sleek
    0.06
     exhaust
    0.06
     åĪ
    0.06
    achts
    0.06
    führ
    0.05
    Activations Density 0.015%

    No Known Activations