© 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. 79021
    Prev
    Next
    INDEX
    Explanations

    references to individuals or entities associated with controversial or significant studies and opinions

    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
    ieves
    -0.07
    gross
    -0.07
     ÑĦоÑĢ
    -0.06
     mutual
    -0.06
     Leban
    -0.06
    çĩķ
    -0.06
     Lump
    -0.06
    533
    -0.06
    years
    -0.06
     gross
    -0.06
    POSITIVE LOGITS
    Transmission
    0.10
     Transmission
    0.10
     transmission
    0.08
     transmissions
    0.07
     transmitting
    0.07
    æ¿ĥ
    0.07
    anh
    0.07
     slightly
    0.07
    æŁĵ
    0.07
    oq
    0.06
    Activations Density 0.001%

    No Known Activations