© 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. 128855
    Prev
    Next
    INDEX
    Explanations

    instances of sorting and returning values in programming contexts

    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
    axter
    -0.06
     yaw
    -0.06
     holog
    -0.06
     Townsend
    -0.06
     hopefully
    -0.06
    uppen
    -0.06
     законом
    -0.06
    ataka
    -0.06
    _NAMESPACE
    -0.06
    ence
    -0.06
    POSITIVE LOGITS
     instead
    0.11
    instead
    0.10
     вмеÑģÑĤ
    0.08
     Instead
    0.08
    Instead
    0.07
    ils
    0.07
    ãģĹãģ¾ãģĨ
    0.07
    æĪIJäºĨ
    0.07
    λμ
    0.07
    óz
    0.06
    Activations Density 0.030%

    No Known Activations