© 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. 76066
    Prev
    Next
    INDEX
    Explanations

    conditional statements involving comparisons and checks in programming code

    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
    .scalablytyped
    -0.08
    olini
    -0.07
    gons
    -0.06
    onus
    -0.06
    ayar
    -0.06
    dum
    -0.06
    odable
    -0.06
     Correct
    -0.06
     oku
    -0.06
    ingo
    -0.06
    POSITIVE LOGITS
     too
    0.08
     lacked
    0.08
     cannot
    0.07
    too
    0.07
     TOO
    0.07
     insufficient
    0.07
     fail
    0.07
     fails
    0.07
     lacks
    0.07
     lacking
    0.07
    Activations Density 0.060%

    No Known Activations