© 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. 39874
    Prev
    Next
    INDEX
    Explanations

    mentions of categories and forums

    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
    antal
    -0.06
    atum
    -0.06
    uch
    -0.06
     Peek
    -0.06
    itr
    -0.06
    oku
    -0.06
    ech
    -0.06
    еÑĪ
    -0.06
    lug
    -0.06
    enty
    -0.06
    POSITIVE LOGITS
    /frontend
    0.07
    dez
    0.07
    villa
    0.07
    ine
    0.07
    .hxx
    0.06
    çĢ¬
    0.06
    Bang
    0.06
     sess
    0.06
    acades
    0.06
     trừ
    0.06
    Activations Density 0.001%

    No Known Activations