© 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. 15-LLAMASCOPE-RES-131K
    11. 103295
    Prev
    Next
    INDEX
    Explanations

    instances of communication about events or news

    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
    ektir
    -0.07
    reesome
    -0.07
    UnitTest
    -0.07
    ÑģÑıÑĩ
    -0.07
    -thumbnails
    -0.07
    izin
    -0.07
     eiusmod
    -0.07
    -vars
    -0.07
    ÅĽ
    -0.06
    eks
    -0.06
    POSITIVE LOGITS
    onus
    0.07
    eli
    0.06
    oni
    0.06
     lead
    0.06
    uchs
    0.06
    anda
    0.06
     cand
    0.06
    .fm
    0.06
     spokeswoman
    0.05
     necessarily
    0.05
    Activations Density 0.016%

    No Known Activations