© 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. 118588
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to offenses and regulations

    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
    ,
    -0.06
    lag
    -0.06
    tic
    -0.06
     fer
    -0.05
     Mission
    -0.05
     courtesy
    -0.05
    letter
    -0.05
    map
    -0.05
     auto
    -0.05
     instead
    -0.05
    POSITIVE LOGITS
     knowingly
    0.11
    actus
    0.09
    ãĥ¼ãĥ©
    0.09
    RefCount
    0.08
    kke
    0.07
    WithContext
    0.07
     treff
    0.07
     æĵ
    0.07
    éı¡
    0.07
    reamble
    0.07
    Activations Density 0.040%

    No Known Activations