© 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. 29422
    Prev
    Next
    INDEX
    Explanations

    phrases related to event planning and entertainment advertisement

    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
    iew
    -0.07
     @}
    -0.07
    ovsky
    -0.07
    Copyright
    -0.06
    .gl
    -0.06
    attr
    -0.06
    uve
    -0.06
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.06
    евиÑĩ
    -0.06
     (!!
    -0.06
    POSITIVE LOGITS
     hol
    0.07
     pi
    0.07
    pi
    0.07
    540
    0.06
    294
    0.06
    å¸Į
    0.06
    SCALL
    0.06
     Hello
    0.06
    awner
    0.06
    umbnail
    0.06
    Activations Density 0.012%

    No Known Activations