Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 96006
    Prev
    Next
    INDEX
    Explanations

    references to environmental variables in a programming context

    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
    ogle
    -0.08
    ponge
    -0.07
    ControlItem
    -0.07
    ograd
    -0.07
    okie
    -0.07
    алÑĸв
    -0.07
    ÙĪØ¯Ùĩ
    -0.07
    ffe
    -0.07
    auga
    -0.07
    #index
    -0.07
    POSITIVE LOGITS
    th
    0.06
     surrounding
    0.06
    SR
    0.06
     ****************************************************************************
    0.06
    .nih
    0.05
    rd
    0.05
     Surround
    0.05
    len
    0.05
    redirectTo
    0.05
    .ssl
    0.05
    Activations Density 0.010%

    No Known Activations