© 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. 9-LLAMASCOPE-RES-131K
    11. 96317
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and functions, especially those associated with data handling

    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
    zbek
    -0.08
    -alist
    -0.08
    PEAT
    -0.07
    Systems
    -0.07
    vest
    -0.07
    pread
    -0.07
     Clarkson
    -0.07
    ãĥ¬ãĥĥãĥĪ
    -0.07
    olumn
    -0.07
    OLEAN
    -0.07
    POSITIVE LOGITS
    usch
    0.06
    fulness
    0.06
    estate
    0.05
    indle
    0.05
    ëij
    0.05
    jour
    0.05
     critical
    0.05
     Slo
    0.05
    -
    0.05
     transitional
    0.05
    Activations Density 0.001%

    No Known Activations