© 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. 15-LLAMASCOPE-RES-131K
    11. 87711
    Prev
    Next
    INDEX
    Explanations

    titles and roles of officials and political figures

    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
    otros
    -0.07
    Äĥn
    -0.07
    çĶ²
    -0.07
    pesan
    -0.06
    uben
    -0.06
    zept
    -0.06
    moth
    -0.06
    kola
    -0.06
    veau
    -0.06
    lection
    -0.06
    POSITIVE LOGITS
    erli
    0.07
    angu
    0.06
    973
    0.06
    847
    0.06
    座
    0.06
     bil
    0.06
    czy
    0.06
    .sdk
    0.06
    éħ
    0.06
     ï¾
    0.06
    Activations Density 0.015%

    No Known Activations