© 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. 62431
    Prev
    Next
    INDEX
    Explanations

    geographic regions and countries associated with manufacturing

    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
    úi
    -0.09
    ì¢ħ
    -0.07
    548
    -0.07
    Ñĥмов
    -0.07
     Ngh
    -0.07
    onian
    -0.07
    .hwp
    -0.06
     åĵģ
    -0.06
    ongoose
    -0.06
    _LCD
    -0.06
    POSITIVE LOGITS
    ia
    0.06
     Fallen
    0.06
    ½Ķ
    0.06
     Bail
    0.06
    uset
    0.06
     Sha
    0.06
     bas
    0.06
    ิà¹Ģศษ
    0.06
    mania
    0.06
     Anonymous
    0.05
    Activations Density 0.002%

    No Known Activations