© 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. 82023
    Prev
    Next
    INDEX
    Explanations

    themes related to psychological phenomena and emotional experiences

    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
    egin
    -0.07
    ntl
    -0.07
    oplan
    -0.07
    irst
    -0.07
    iece
    -0.07
    ailure
    -0.06
    addColumn
    -0.06
     конÑĤÑĢа
    -0.06
    olesterol
    -0.06
    _ARGUMENT
    -0.06
    POSITIVE LOGITS
     cases
    0.07
    cases
    0.07
     Reports
    0.06
     subs
    0.06
     reports
    0.06
    èĮĥ
    0.06
    witch
    0.06
     ph
    0.06
    ect
    0.06
     ect
    0.06
    Activations Density 0.009%

    No Known Activations