© 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. 4853
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory terms related to emotional and psychological states

    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
    clud
    -0.07
    ɵ
    -0.06
     regards
    -0.06
     detriment
    -0.06
     diz
    -0.06
    kinson
    -0.06
    eras
    -0.06
     behalf
    -0.06
    ospace
    -0.06
    ocate
    -0.05
    POSITIVE LOGITS
     presence
    0.08
     å¼
    0.07
    FAULT
    0.07
     cÃłng
    0.07
    ccb
    0.07
     combination
    0.07
    iber
    0.07
     totiž
    0.07
    ëĿ¼ëĬĶ
    0.07
    adal
    0.07
    Activations Density 0.083%

    No Known Activations