© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127458
    Prev
    Next
    INDEX
    Explanations

    discussions related to legislation and legal implications

    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
    ↵↵
    -0.07
    kur
    -0.06
     tens
    -0.06
    reste
    -0.06
    Ø®ÛĮ
    -0.06
    -Series
    -0.06
    â̬
    -0.06
     yandan
    -0.06
    ãģ¾ãģĻ
    -0.06
    -series
    -0.06
    POSITIVE LOGITS
    ihad
    0.06
     (!((
    0.06
    åĭ
    0.06
    asca
    0.06
    ãĥ³ãĥĩãĤ£
    0.06
     Harness
    0.06
     hadn
    0.06
    ãģ§ãģĤãģ£ãģŁ
    0.06
     cages
    0.06
    ëĮĢíķĻ
    0.06
    Activations Density 0.001%

    No Known Activations