© 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. 17-LLAMASCOPE-RES-131K
    11. 40650
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce explanations or justifications

    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
    eking
    -0.07
    umph
    -0.06
    oras
    -0.06
    iji
    -0.06
    oks
    -0.06
     Aires
    -0.06
    enko
    -0.06
    cin
    -0.06
    mbH
    -0.06
     either
    -0.05
    POSITIVE LOGITS
     Called
    0.07
     called
    0.07
    chia
    0.07
    åı«
    0.07
     Synd
    0.06
    called
    0.06
     Lov
    0.06
    ÙĬد
    0.06
    ']!='
    0.06
    Lov
    0.06
    Activations Density 0.003%

    No Known Activations