© 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. 28527
    Prev
    Next
    INDEX
    Explanations

    conditional clauses and exceptions in rules or policies

    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
    tvrt
    -0.07
    atform
    -0.07
    IME
    -0.07
    ighet
    -0.07
    мени
    -0.06
    úi
    -0.06
    adan
    -0.06
    arLayout
    -0.06
     structural
    -0.06
    aday
    -0.06
    POSITIVE LOGITS
    Trou
    0.06
    mo
    0.06
     Guth
    0.06
    alin
    0.06
    yna
    0.06
     Cec
    0.06
    bulk
    0.06
     nebu
    0.06
     Stanton
    0.06
    ynn
    0.06
    Activations Density 0.002%

    No Known Activations