© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27184
    Prev
    Next
    INDEX
    Explanations

    names of products and brands

    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
     roughly
    -0.06
     famously
    -0.06
    Ī
    -0.06
     ↵
    -0.06
    biased
    -0.06
    221
    -0.05
    ipa
    -0.05
    _patterns
    -0.05
     strictly
    -0.05
    _less
    -0.05
    POSITIVE LOGITS
    ï¿
    0.09
    asca
    0.07
    ieber
    0.07
    prt
    0.07
    elib
    0.07
    adol
    0.07
    OptionsResolver
    0.07
    \Type
    0.07
     UPDATED
    0.07
    ĶåĽŀ
    0.06
    Activations Density 0.048%

    No Known Activations