© 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. 22-LLAMASCOPE-RES-131K
    11. 3922
    Prev
    Next
    INDEX
    Explanations

    coding best practices and style guidelines

    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
    .EventQueue
    -0.06
    å§
    -0.06
    IGNORE
    -0.06
    /fast
    -0.06
    ollo
    -0.06
    .stringify
    -0.06
     Morph
    -0.06
    reu
    -0.05
    illation
    -0.05
    _claim
    -0.05
    POSITIVE LOGITS
     ban
    0.07
    elseif
    0.07
    ICAST
    0.07
     Ban
    0.07
    CAST
    0.07
     banned
    0.07
     Bris
    0.07
    Ban
    0.07
     excessive
    0.06
    ivent
    0.06
    Activations Density 0.005%

    No Known Activations