© 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. 15-LLAMASCOPE-RES-131K
    6. 1294
    Prev
    Next
    INDEX
    Explanations

    references to software features or technological components

    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
    à¸IJ
    -0.07
    laps
    -0.07
    jang
    -0.06
    yh
    -0.06
    еп
    -0.06
    ezi
    -0.06
    วล
    -0.06
    од
    -0.06
    ,System
    -0.06
    elor
    -0.06
    POSITIVE LOGITS
     social
    0.07
     Social
    0.07
    .social
    0.06
    ä¸ģ
    0.06
    toolbar
    0.06
     trib
    0.06
    _timeline
    0.06
    ãĥ³ãĥģ
    0.06
     Glen
    0.06
     plug
    0.06
    Activations Density 0.000%

    No Known Activations