© 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. 9-LLAMASCOPE-RES-131K
    11. 97217
    Prev
    Next
    INDEX
    Explanations

    programming language constructs related to state management

    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
    å¨ĺ
    -0.07
    intl
    -0.07
    ÏįÏĢ
    -0.06
    edor
    -0.06
    еÑĤи
    -0.06
    вÑĸÑĤ
    -0.06
     swe
    -0.06
     ëĦ
    -0.06
    alis
    -0.06
    estr
    -0.06
    POSITIVE LOGITS
     Morav
    0.07
    thouse
    0.07
    733
    0.06
    ÑĢÑĥз
    0.06
    MBOL
    0.06
    781
    0.06
    ÅĤ
    0.06
     AndAlso
    0.06
    gro
    0.06
     Alonso
    0.06
    Activations Density 0.046%

    No Known Activations