© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5961
    Prev
    Next
    INDEX
    Explanations

    phrases related to protection and security, especially in the context of national and personal interests

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    imate
    -0.08
    isos
    -0.07
    Ì
    -0.07
    ÌĨ
    -0.07
    azio
    -0.07
    eger
    -0.07
    inear
    -0.07
    statt
    -0.07
    enced
    -0.06
    _defs
    -0.06
    POSITIVE LOGITS
     against
    0.14
    against
    0.11
     Against
    0.10
    Against
    0.10
     interests
    0.10
     vulnerable
    0.09
     fragile
    0.08
     khá»ıi
    0.08
     rights
    0.08
     assets
    0.08
    Activations Density 0.019%

    No Known Activations