© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1005
    Prev
    Next
    INDEX
    Explanations

    elements and functions related to dataframes in programming contexts

    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
    sted
    -0.07
     Canc
    -0.06
     canc
    -0.06
    (s
    -0.06
    ph
    -0.06
     диÑĢекÑĤоÑĢ
    -0.06
    LAY
    -0.06
     Rack
    -0.05
    OLID
    -0.05
     arreglo
    -0.05
    POSITIVE LOGITS
    auce
    0.07
    ÑģÑĤеÑĢ
    0.07
    ñana
    0.07
    isman
    0.07
    anium
    0.07
    oucher
    0.07
    shan
    0.06
    ertino
    0.06
     ActionTypes
    0.06
    /Foundation
    0.06
    Activations Density 0.003%

    No Known Activations