© 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. 60888
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight exceptions or specific instances within a broader 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
    instr
    -0.07
    ën
    -0.07
    inz
    -0.07
    ocha
    -0.07
    кÑĢа
    -0.06
    574
    -0.06
    inas
    -0.06
    лÑĸд
    -0.06
    amac
    -0.06
    -IN
    -0.06
    POSITIVE LOGITS
     case
    0.12
     in
    0.12
     neste
    0.10
     caso
    0.10
     cases
    0.10
    åł´åIJĪãģ¯
    0.09
     here
    0.09
     Case
    0.09
    case
    0.09
    à¸ģรà¸ĵ
    0.09
    Activations Density 0.115%

    No Known Activations