© 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. 15-LLAMASCOPE-RES-131K
    11. 89256
    Prev
    Next
    INDEX
    Explanations

    conditional statements and logical comparisons used in programming

    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
    nds
    -0.07
    peria
    -0.07
    åŀ
    -0.06
    sei
    -0.06
    utow
    -0.06
     mantle
    -0.06
    PerPage
    -0.06
    _click
    -0.06
    LOAT
    -0.06
    ÑĢоÑī
    -0.06
    POSITIVE LOGITS
    iami
    0.06
     Minimum
    0.06
     minimum
    0.06
    asan
    0.06
    asad
    0.06
     min
    0.06
     SetLastError
    0.05
     âĿ
    0.05
    odzi
    0.05
    ocha
    0.05
    Activations Density 0.022%

    No Known Activations