© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87525
    Prev
    Next
    INDEX
    Explanations

    phrases asserting beliefs or perspectives about specific issues

    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
     Rencontres
    -0.07
    _CONVERT
    -0.07
    oshi
    -0.07
    -disable
    -0.06
     hed
    -0.06
    rell
    -0.06
     isEqual
    -0.06
    _customize
    -0.06
    etary
    -0.06
    ligt
    -0.06
    POSITIVE LOGITS
     this
    0.08
    dyby
    0.06
     deserves
    0.06
     should
    0.06
    оÑĢалÑĮ
    0.06
     deserve
    0.06
    галÑĸ
    0.06
    tera
    0.06
    INGS
    0.06
     nên
    0.06
    Activations Density 0.024%

    No Known Activations