© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 79807
    Prev
    Next
    INDEX
    Explanations

    key information regarding financial aid and partnerships related to water management

    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
    Ñģед
    -0.07
     recess
    -0.07
     simp
    -0.06
    ETERS
    -0.06
    )view
    -0.06
    openhagen
    -0.06
    å¿
    -0.06
     flat
    -0.06
    stoff
    -0.06
    θμ
    -0.06
    POSITIVE LOGITS
    program
    0.10
     Program
    0.10
     program
    0.10
     project
    0.10
     programme
    0.09
    project
    0.08
    oproject
    0.08
    Program
    0.08
     programa
    0.08
     programma
    0.08
    Activations Density 0.016%

    No Known Activations