© 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. 3103
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific studies on plastic materials

    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
    emark
    -0.06
    ator
    -0.06
    ries
    -0.06
     Nest
    -0.06
     torque
    -0.06
     circus
    -0.06
    еÑĢÑĮ
    -0.06
     elasticity
    -0.05
     célib
    -0.05
    bird
    -0.05
    POSITIVE LOGITS
     night
    0.07
     oslo
    0.07
     light
    0.07
     WaitForSeconds
    0.07
    ноÑĩ
    0.07
    çģ¯
    0.07
    ssp
    0.07
    दर
    0.07
     lit
    0.07
    สà¸Ķ
    0.07
    Activations Density 0.009%

    No Known Activations