© 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. 22-LLAMASCOPE-RES-131K
    11. 3867
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotional or subjective 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
    .updateDynamic
    -0.10
    //{{
    -0.09
    çĶ³åįļ
    -0.09
    formace
    -0.09
    @nate
    -0.09
    .yy
    -0.09
    jedn
    -0.09
     RuntimeMethod
    -0.09
     ÑĤоже
    -0.09
    ycastle
    -0.08
    POSITIVE LOGITS
    âĢ¦the
    0.08
     ‘
    0.08
     [
    0.07
     âĢ¦
    0.07
     âĢ¦↵
    0.07
     [âĢ¦]
    0.07
    âĢ¦
    0.06
     basically
    0.06
    ](
    0.06
     '
    0.06
    Activations Density 0.260%

    No Known Activations