© 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. 56865
    Prev
    Next
    INDEX
    Explanations

    emotional responses and reflections on consequences

    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
    erus
    -0.07
    ÅĪ
    -0.07
     renewed
    -0.07
    erta
    -0.07
    zn
    -0.06
    tractor
    -0.06
    rette
    -0.06
     اÙĦÙħÙĪس
    -0.06
    WithName
    -0.06
    usher
    -0.06
    POSITIVE LOGITS
     regret
    0.17
     regrets
    0.16
     remorse
    0.09
     later
    0.09
     repent
    0.08
    later
    0.08
     Reg
    0.08
     piÅŁ
    0.08
     consequences
    0.07
    åIJİ
    0.07
    Activations Density 0.040%

    No Known Activations