© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 41287
    Prev
    Next
    INDEX
    Explanations

    comparisons of economic performance between countries

    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
    ãĥĨãĥ«
    -0.08
     Blasio
    -0.08
    ANNEL
    -0.08
    enary
    -0.08
    esi
    -0.08
    ikler
    -0.08
    entious
    -0.07
    oload
    -0.07
    _NULL
    -0.07
    .appspot
    -0.07
    POSITIVE LOGITS
     overt
    0.13
     surpass
    0.10
     surpassed
    0.09
     become
    0.08
     now
    0.08
     equal
    0.08
     second
    0.07
     equality
    0.07
     replace
    0.07
     ahead
    0.07
    Activations Density 0.101%

    No Known Activations