© 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. 77680
    Prev
    Next
    INDEX
    Explanations

    expressions related to emotions and physical interactions

    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
    /process
    -0.08
    cala
    -0.07
    ales
    -0.07
    ality
    -0.07
    esty
    -0.07
    oids
    -0.07
    /system
    -0.07
    /software
    -0.07
    ultan
    -0.07
    illisecond
    -0.07
    POSITIVE LOGITS
    tings
    0.06
    ings
    0.06
    ibr
    0.06
    bum
    0.06
    apr
    0.06
    ĥn
    0.06
     Amend
    0.06
     Belg
    0.06
    adera
    0.06
    -worthy
    0.06
    Activations Density 0.035%

    No Known Activations