© 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 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. 15-LLAMASCOPE-RES-131K
    11. 88281
    Prev
    Next
    INDEX
    Explanations

    numerical quantities, particularly large figures related to populations and statistics

    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
    emd
    -0.07
    alam
    -0.06
    rost
    -0.06
    ble
    -0.06
    cott
    -0.05
    #echo
    -0.05
    phalt
    -0.05
    ulan
    -0.05
    ankan
    -0.05
    ynet
    -0.05
    POSITIVE LOGITS
    aires
    0.10
    ombo
    0.09
    htar
    0.08
    Ø´Ùĩ
    0.08
    aire
    0.08
    abaj
    0.08
    phants
    0.07
    naire
    0.07
    ittest
    0.07
    doll
    0.07
    Activations Density 0.058%

    No Known Activations