© 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. 17-LLAMASCOPE-RES-131K
    11. 41566
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize personal experiences and actions

    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
    Hopefully
    -0.08
    ordion
    -0.08
     Hopefully
    -0.07
     hopefully
    -0.07
    aka
    -0.07
     yesterday
    -0.07
    athe
    -0.07
    ÃĴ
    -0.06
     hopes
    -0.06
     Yesterday
    -0.06
    POSITIVE LOGITS
     Credit
    0.07
    vest
    0.07
    uster
    0.06
    USTER
    0.06
    UGHT
    0.06
    éĻ£
    0.06
     originally
    0.06
     byÅĤo
    0.06
    vor
    0.06
    enz
    0.06
    Activations Density 0.029%

    No Known Activations