© 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. 17-LLAMASCOPE-RES-131K
    6. 129317
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software version control and security vulnerabilities

    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
     Replacement
    -0.07
    reh
    -0.07
    κÎŃ
    -0.06
    .gs
    -0.06
     Movement
    -0.06
     GSL
    -0.06
    ilot
    -0.06
     movement
    -0.06
    movement
    -0.06
    estroy
    -0.06
    POSITIVE LOGITS
     switched
    0.10
     switch
    0.10
     switching
    0.09
     mixed
    0.09
     Switch
    0.09
    _switch
    0.09
    switch
    0.08
     Mixed
    0.08
    Mixed
    0.08
    .switch
    0.08
    Activations Density 0.010%

    No Known Activations