© 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. 88846
    Prev
    Next
    INDEX
    Explanations

    the structure and organization of research studies and statistical results

    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
    Å¡li
    -0.07
    ?,?,?,?,
    -0.07
    ully
    -0.07
    -,
    -0.06
    arger
    -0.06
     ZemÄĽ
    -0.06
    à¸ŀร
    -0.06
    ulario
    -0.06
    à¥ĭà¤Ĥ,
    -0.06
    REFIX
    -0.06
    POSITIVE LOGITS
    以åıĬ
    0.07
    emark
    0.06
    ãģĿãģĹãģ¦
    0.06
    dera
    0.06
    ia
    0.06
    ','');↵
    0.06
    ëŀij
    0.05
    istro
    0.05
     intermediary
    0.05
    .Qt
    0.05
    Activations Density 0.128%

    No Known Activations