© 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. 3460
    Prev
    Next
    INDEX
    Explanations

    references to economic relationships and impacts

    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
    Latch
    -0.07
    aman
    -0.07
    Ñıб
    -0.07
    CURRENT
    -0.07
    egas
    -0.06
    оÑĢаз
    -0.06
    amel
    -0.06
     reklam
    -0.06
    имо
    -0.06
    chap
    -0.06
    POSITIVE LOGITS
     now
    0.28
     ÑĤепеÑĢÑĮ
    0.23
    now
    0.21
     Now
    0.20
     ahora
    0.19
    Now
    0.18
     NOW
    0.18
     agora
    0.17
     ìĿ´ìłľ
    0.17
    	now
    0.16
    Activations Density 0.087%

    No Known Activations