© 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. 16986
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to mathematical proofs and lemmas

    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
    Ñ
    -0.07
    icaret
    -0.07
    ouser
    -0.07
    regon
    -0.06
    bic
    -0.06
    SystemService
    -0.06
    ãĤĵãģ©
    -0.06
    ̣
    -0.06
    ika
    -0.06
    getRepository
    -0.06
    POSITIVE LOGITS
    _proof
    0.14
     proof
    0.13
     Proof
    0.12
    Proof
    0.12
    proof
    0.12
     proofs
    0.12
    -proof
    0.10
     prove
    0.10
    è¯ģæĺİ
    0.09
     prova
    0.08
    Activations Density 0.209%

    No Known Activations