© 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. 60030
    Prev
    Next
    INDEX
    Explanations

    references to Twitter and its co-founders, alongside related discussions about tweets and engagement on the platform

    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
    resco
    -0.08
    qua
    -0.07
     Bristol
    -0.07
    /XMLSchema
    -0.06
    orch
    -0.06
     Kra
    -0.06
    ute
    -0.06
     Bauer
    -0.06
    sect
    -0.06
    nant
    -0.06
    POSITIVE LOGITS
    deo
    0.08
    ĶåĽŀ
    0.07
    дина
    0.07
    åĻ
    0.07
     Merc
    0.07
    .twimg
    0.07
     Piper
    0.07
     Bird
    0.06
    alsex
    0.06
    Paginator
    0.06
    Activations Density 0.009%

    No Known Activations