© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96490
    Prev
    Next
    INDEX
    Explanations

    major headings or titles related to various topics or categories

    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
    ella
    -0.08
    eç
    -0.08
    oya
    -0.08
    olf
    -0.08
    ullo
    -0.07
    ázev
    -0.07
    edio
    -0.07
    ãĤ¤ãĥĦ
    -0.07
     Expansion
    -0.07
    eck
    -0.07
    POSITIVE LOGITS
     Bull
    0.07
     Bor
    0.06
    ew
    0.06
     Shank
    0.06
     Jun
    0.05
     mainstream
    0.05
     cannot
    0.05
    à¥Īत
    0.05
     ev
    0.05
     lapse
    0.05
    Activations Density 0.001%

    No Known Activations