© 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. 59885
    Prev
    Next
    INDEX
    Explanations

    content related to event posting and promotional advertising

    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
    ارج
    -0.07
     Eisen
    -0.07
     kanal
    -0.06
    å¥ij
    -0.06
    iram
    -0.06
    istrovstvÃŃ
    -0.06
     Farmer
    -0.06
     Liberties
    -0.06
    /tiny
    -0.06
    leaflet
    -0.06
    POSITIVE LOGITS
    azar
    0.07
    iveau
    0.07
    ffer
    0.06
    CCC
    0.06
     handc
    0.06
    emme
    0.06
    agan
    0.06
    639
    0.06
    699
    0.06
    EG
    0.06
    Activations Density 0.020%

    No Known Activations