© 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. 15-LLAMASCOPE-RES-131K
    11. 26713
    Prev
    Next
    INDEX
    Explanations

    age-related details and admission information for events or places

    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
    .shtml
    -0.08
     Zus
    -0.07
    anka
    -0.06
    wl
    -0.06
    gest
    -0.06
    yna
    -0.06
    idan
    -0.06
    ysi
    -0.06
    äl
    -0.06
    oid
    -0.06
    POSITIVE LOGITS
    brtc
    0.07
    afx
    0.06
    919
    0.06
    大人
    0.06
    cores
    0.06
    oland
    0.06
    iami
    0.06
     Bryan
    0.06
    ushman
    0.06
     deem
    0.06
    Activations Density 0.006%

    No Known Activations