© 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. 125119
    Prev
    Next
    INDEX
    Explanations

    expressions indicating uncertainty or asking for clarification

    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
     trib
    -0.06
    acio
    -0.06
    wich
    -0.06
     Fuji
    -0.05
    ãĥ¼ãĥĸ
    -0.05
    angu
    -0.05
    eties
    -0.05
    Imagine
    -0.05
     pro
    -0.05
    indi
    -0.05
    POSITIVE LOGITS
    ackers
    0.08
     thanks
    0.08
     thank
    0.08
    éijij
    0.08
     yes
    0.07
    esda
    0.07
    ursal
    0.07
    @js
    0.07
    CKER
    0.07
    è¡£
    0.07
    Activations Density 0.017%

    No Known Activations