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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28461
    Prev
    Next
    INDEX
    Explanations

    negative emotions and the concepts of betrayal or rejection

    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
    gen
    -0.06
    401
    -0.06
     uncon
    -0.06
    526
    -0.06
    å¿ĺ
    -0.06
    optera
    -0.06
     ALS
    -0.05
    403
    -0.05
     Unsigned
    -0.05
    099
    -0.05
    POSITIVE LOGITS
    sie
    0.08
    inki
    0.08
    úi
    0.07
    å¤ķ
    0.07
     surv
    0.07
    atem
    0.07
    okane
    0.07
     dove
    0.07
    sik
    0.06
    atos
    0.06
    Activations Density 0.001%

    No Known Activations