© 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. 17-LLAMASCOPE-RES-131K
    11. 120293
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and structures

    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
    sÃŃ
    -0.07
     trov
    -0.06
    olicit
    -0.06
    atsby
    -0.06
    kup
    -0.05
    antan
    -0.05
     -
    -0.05
    .mi
    -0.05
    aland
    -0.05
    ylv
    -0.05
    POSITIVE LOGITS
    nger
    0.07
    ãĥ³ãĥī
    0.07
    .setter
    0.07
     UIEdgeInsets
    0.06
    -touch
    0.06
    isin
    0.06
    Lifecycle
    0.06
    ÏĮγ
    0.06
    WidgetItem
    0.06
    ë²Į
    0.06
    Activations Density 0.001%

    No Known Activations