© 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. 126446
    Prev
    Next
    INDEX
    Explanations

    mentions of data breach notification laws 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
     aks
    -0.06
    IEW
    -0.06
    ------+
    -0.06
    Ãłng
    -0.06
    赤
    -0.05
    lew
    -0.05
    Ïĥιμο
    -0.05
    lev
    -0.05
     ol
    -0.05
    ritch
    -0.05
    POSITIVE LOGITS
    risk
    0.08
     risk
    0.08
    Topics
    0.07
    Risk
    0.07
     Risk
    0.07
     Lage
    0.07
     moll
    0.06
     mismatch
    0.06
    ieder
    0.06
    ril
    0.06
    Activations Density 0.151%

    No Known Activations