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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 73674
    Prev
    Next
    INDEX
    Explanations

    expressions of strong emotions, particularly those related to feelings of despair or profound change

    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
     اÙĦØ£Ùħر
    -0.06
    åįĪ
    -0.06
    kv
    -0.06
    tir
    -0.06
     khá
    -0.06
     rád
    -0.06
    EDA
    -0.06
     agre
    -0.06
    agas
    -0.06
    _FMT
    -0.05
    POSITIVE LOGITS
    occo
    0.07
    istol
    0.07
     amounts
    0.07
    errer
    0.07
    errupt
    0.06
     amount
    0.06
    liter
    0.06
    ãģĬãĤĬ
    0.06
    ilter
    0.06
    ownt
    0.06
    Activations Density 0.060%

    No Known Activations