© 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. 74321
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal experiences and reflections

    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
     intr
    -0.07
    aston
    -0.06
    eroon
    -0.06
     Rim
    -0.06
     prod
    -0.06
    ients
    -0.06
    TabPage
    -0.06
     co
    -0.06
     Cup
    -0.06
    AMY
    -0.06
    POSITIVE LOGITS
    éĢĶ
    0.12
     stopped
    0.08
    éģĩ
    0.08
    (stop
    0.07
     Stops
    0.07
     stops
    0.07
     carrying
    0.07
     rencontr
    0.07
     stopping
    0.07
    -stop
    0.07
    Activations Density 0.045%

    No Known Activations