© 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 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. 17-LLAMASCOPE-RES-131K
    11. 75054
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data manipulation functions within code

    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
    ayan
    -0.06
    altet
    -0.06
    unch
    -0.06
     Tits
    -0.06
     اÙĦÙĩ
    -0.06
    ARP
    -0.06
    alt
    -0.06
    allet
    -0.06
    inati
    -0.06
    -force
    -0.06
    POSITIVE LOGITS
    estone
    0.07
    100
    0.07
     ten
    0.07
    10
    0.07
    ych
    0.07
    /uploads
    0.06
    ignKey
    0.06
    -test
    0.06
    ระ
    0.06
    足
    0.06
    Activations Density 0.019%

    No Known Activations