© 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. 126594
    Prev
    Next
    INDEX
    Explanations

    conditional statements and clauses related to function execution and argument validation

    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
    оÑĢаÑı
    -0.07
    ıc
    -0.06
     Fate
    -0.06
    uler
    -0.06
    icontrol
    -0.06
    ffiti
    -0.06
    .Reporting
    -0.06
    agenta
    -0.06
    NX
    -0.06
     behalf
    -0.06
    POSITIVE LOGITS
    iele
    0.07
     multiple
    0.06
    astos
    0.06
    ÑĪев
    0.06
    zell
    0.06
    лек
    0.06
    atürk
    0.06
     bar
    0.06
    į°ìĿ´
    0.06
    apper
    0.06
    Activations Density 0.025%

    No Known Activations