© 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. 5-LLAMASCOPE-RES-131K
    11. 126766
    Prev
    Next
    INDEX
    Explanations

    CSS pseudo-selectors and properties related to user interface elements

    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
    ché
    -0.06
    inha
    -0.06
    elly
    -0.06
    querque
    -0.05
    okin
    -0.05
     Kirk
    -0.05
    315
    -0.05
    ekil
    -0.05
     autonom
    -0.05
     -:-
    -0.05
    POSITIVE LOGITS
    å¹²
    0.07
    ForObject
    0.07
     oranı
    0.07
    .authorization
    0.06
    ange
    0.06
    -chart
    0.06
    LLU
    0.06
    EMPL
    0.06
    &view
    0.06
    Ïģίζ
    0.06
    Activations Density 0.001%

    No Known Activations