© 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 EvalsExportsinterp-engineNEWAPI 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. 120225
    Prev
    Next
    INDEX
    Explanations

    sequences of characters that represent formatting or encoding data, such as character references

    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
    s
    -0.06
     [
    -0.06
    iser
    -0.06
    er
    -0.06
     wing
    -0.05
    ÑĢÑĥк
    -0.05
    ble
    -0.05
    ple
    -0.05
    wer
    -0.05
    outers
    -0.05
    POSITIVE LOGITS
     cih
    0.08
    ç£
    0.08
    ÏĮÏģ
    0.08
    emoc
    0.08
    ZeroWidthSpace
    0.07
    ellipsis
    0.07
    ãģıãģł
    0.07
    ÅĻes
    0.07
     Hakk
    0.07
    etur
    0.07
    Activations Density 0.054%

    No Known Activations